public inbox for [email protected]  
help / color / mirror / Atom feed
[PATCH v24 3/5] Make archiver process an auxiliary process
283+ messages / 9 participants
[nested] [flat]

* [PATCH v24 3/5] Make archiver process an auxiliary process
@ 2018-11-07 07:53  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2018-11-07 07:53 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.
Archiver process must be a auxiliary process since it uses shared
memory after stats data wes moved onto shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/bootstrap/bootstrap.c   |  8 +++
 src/backend/postmaster/pgarch.c     | 98 +++++++----------------------
 src/backend/postmaster/pgstat.c     |  6 ++
 src/backend/postmaster/postmaster.c | 35 ++++++++---
 src/include/miscadmin.h             |  2 +
 src/include/pgstat.h                |  1 +
 src/include/postmaster/pgarch.h     |  4 +-
 7 files changed, 67 insertions(+), 87 deletions(-)

diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 8ea033610d..6e38f9a3d2 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -329,6 +329,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			case BgWriterProcess:
 				statmsg = pgstat_get_backend_desc(B_BG_WRITER);
 				break;
+			case ArchiverProcess:
+				statmsg = pgstat_get_backend_desc(B_ARCHIVER);
+				break;
 			case CheckpointerProcess:
 				statmsg = pgstat_get_backend_desc(B_CHECKPOINTER);
 				break;
@@ -456,6 +459,11 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			BackgroundWriterMain();
 			proc_exit(1);		/* should never return */
 
+		case ArchiverProcess:
+			/* don't set signals, archiver has its own agenda */
+			PgArchiverMain();
+			proc_exit(1);		/* should never return */
+
 		case CheckpointerProcess:
 			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index f84f882c4c..4342ebdab4 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -77,7 +77,6 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
@@ -96,7 +95,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
 static void pgarch_exit(SIGNAL_ARGS);
 static void ArchSigHupHandler(SIGNAL_ARGS);
 static void ArchSigTermHandler(SIGNAL_ARGS);
@@ -114,75 +112,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -222,8 +151,8 @@ pgarch_forkexec(void)
  *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
  *	since we don't use 'em, it hardly matters...
  */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -255,8 +184,27 @@ PgArchiverMain(int argc, char *argv[])
 static void
 pgarch_exit(SIGNAL_ARGS)
 {
-	/* SIGQUIT means curl up and die ... */
-	exit(1);
+	PG_SETMASK(&BlockSig);
+
+	/*
+	 * We DO NOT want to run proc_exit() callbacks -- we're here because
+	 * shared memory may be corrupted, so we don't want to try to clean up our
+	 * transaction.  Just nail the windows shut and get out of town.  Now that
+	 * there's an atexit callback to prevent third-party code from breaking
+	 * things by calling exit() directly, we have to reset the callbacks
+	 * explicitly to make this work as intended.
+	 */
+	on_exit_reset();
+
+	/*
+	 * Note we do exit(2) not exit(0).  This is to force the postmaster into a
+	 * system reset cycle if some idiot DBA sends a manual SIGQUIT to a random
+	 * backend.  This is necessary precisely because we don't clean up our
+	 * shared memory state.  (The "dead man switch" mechanism in pmsignal.c
+	 * should ensure the postmaster sees this as a crash, too, but no harm in
+	 * being doubly sure.)
+	 */
+	exit(2);
 }
 
 /* SIGHUP signal handler for archiver process */
diff --git a/src/backend/postmaster/pgstat.c b/src/backend/postmaster/pgstat.c
index fabcf31de8..8299d2a435 100644
--- a/src/backend/postmaster/pgstat.c
+++ b/src/backend/postmaster/pgstat.c
@@ -2932,6 +2932,9 @@ pgstat_bestart(void)
 			case StartupProcess:
 				lbeentry.st_backendType = B_STARTUP;
 				break;
+			case ArchiverProcess:
+				beentry->st_backendType = B_ARCHIVER;
+				break;
 			case BgWriterProcess:
 				lbeentry.st_backendType = B_BG_WRITER;
 				break;
@@ -4275,6 +4278,9 @@ pgstat_get_backend_desc(BackendType backendType)
 
 	switch (backendType)
 	{
+		case B_ARCHIVER:
+			backendDesc = "archiver";
+			break;
 		case B_AUTOVAC_LAUNCHER:
 			backendDesc = "autovacuum launcher";
 			break;
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 9ff2832c00..84fda38249 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -146,7 +146,8 @@
 #define BACKEND_TYPE_AUTOVAC	0x0002	/* autovacuum worker process */
 #define BACKEND_TYPE_WALSND		0x0004	/* walsender process */
 #define BACKEND_TYPE_BGWORKER	0x0008	/* bgworker process */
-#define BACKEND_TYPE_ALL		0x000F	/* OR of all the above */
+#define BACKEND_TYPE_ARCHIVER	0x0010	/* archiver process */
+#define BACKEND_TYPE_ALL		0x001F	/* OR of all the above */
 
 #define BACKEND_TYPE_WORKER		(BACKEND_TYPE_AUTOVAC | BACKEND_TYPE_BGWORKER)
 
@@ -539,6 +540,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1785,7 +1787,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3042,7 +3044,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3187,10 +3189,8 @@ reaper(SIGNAL_ARGS)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3438,7 +3438,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3643,6 +3643,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3915,6 +3927,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5190,7 +5203,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5475,6 +5488,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index bc6e03fbc7..1f4db67f3f 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -399,6 +399,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -411,6 +412,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index fe076d823d..65713abc2b 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -718,6 +718,7 @@ typedef struct PgStat_GlobalStats
  */
 typedef enum BackendType
 {
+	B_ARCHIVER,
 	B_AUTOVAC_LAUNCHER,
 	B_AUTOVAC_WORKER,
 	B_BACKEND,
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index 2474eac26a..88f16863d4 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
-- 
2.23.0


----Next_Part(Tue_Dec__3_17_27_59_2019_887)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v24-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH 3/5] Make archiver process an auxiliary process
@ 2018-11-07 07:53  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2018-11-07 07:53 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.
Archiver process must be a auxiliary process since it uses shared
memory after stats data wes moved onto shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/bootstrap/bootstrap.c   |  8 +++
 src/backend/postmaster/pgarch.c     | 98 +++++++----------------------
 src/backend/postmaster/pgstat.c     |  6 ++
 src/backend/postmaster/postmaster.c | 43 ++++++++-----
 src/include/miscadmin.h             |  2 +
 src/include/pgstat.h                |  1 +
 src/include/postmaster/pgarch.h     |  4 +-
 7 files changed, 70 insertions(+), 92 deletions(-)

diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index bfc629c753..2f38420313 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -326,6 +326,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			case StartupProcess:
 				statmsg = pgstat_get_backend_desc(B_STARTUP);
 				break;
+			case ArchiverProcess:
+				statmsg = pgstat_get_backend_desc(B_ARCHIVER);
+				break;
 			case BgWriterProcess:
 				statmsg = pgstat_get_backend_desc(B_BG_WRITER);
 				break;
@@ -451,6 +454,11 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			StartupProcessMain();
 			proc_exit(1);		/* should never return */
 
+		case ArchiverProcess:
+			/* don't set signals, archiver has its own agenda */
+			PgArchiverMain();
+			proc_exit(1);		/* should never return */
+
 		case BgWriterProcess:
 			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index 3ca30badb2..6441e69e9a 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -78,7 +78,6 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
@@ -95,7 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
 static void pgarch_exit(SIGNAL_ARGS);
 static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
@@ -111,75 +109,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -219,8 +148,8 @@ pgarch_forkexec(void)
  *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
  *	since we don't use 'em, it hardly matters...
  */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -252,8 +181,27 @@ PgArchiverMain(int argc, char *argv[])
 static void
 pgarch_exit(SIGNAL_ARGS)
 {
-	/* SIGQUIT means curl up and die ... */
-	exit(1);
+	PG_SETMASK(&BlockSig);
+
+	/*
+	 * We DO NOT want to run proc_exit() callbacks -- we're here because
+	 * shared memory may be corrupted, so we don't want to try to clean up our
+	 * transaction.  Just nail the windows shut and get out of town.  Now that
+	 * there's an atexit callback to prevent third-party code from breaking
+	 * things by calling exit() directly, we have to reset the callbacks
+	 * explicitly to make this work as intended.
+	 */
+	on_exit_reset();
+
+	/*
+	 * Note we do exit(2) not exit(0).  This is to force the postmaster into a
+	 * system reset cycle if some idiot DBA sends a manual SIGQUIT to a random
+	 * process.  This is necessary precisely because we don't clean up our
+	 * shared memory state.  (The "dead man switch" mechanism in pmsignal.c
+	 * should ensure the postmaster sees this as a crash, too, but no harm in
+	 * being doubly sure.)
+	 */
+	exit(2);
 }
 
 /* SIGUSR1 signal handler for archiver process */
diff --git a/src/backend/postmaster/pgstat.c b/src/backend/postmaster/pgstat.c
index 51c486bebd..ca5c6376e5 100644
--- a/src/backend/postmaster/pgstat.c
+++ b/src/backend/postmaster/pgstat.c
@@ -2927,6 +2927,9 @@ pgstat_bestart(void)
 			case StartupProcess:
 				lbeentry.st_backendType = B_STARTUP;
 				break;
+			case ArchiverProcess:
+				beentry->st_backendType = B_ARCHIVER;
+				break;
 			case BgWriterProcess:
 				lbeentry.st_backendType = B_BG_WRITER;
 				break;
@@ -4273,6 +4276,9 @@ pgstat_get_backend_desc(BackendType backendType)
 
 	switch (backendType)
 	{
+		case B_ARCHIVER:
+			backendDesc = "archiver";
+			break;
 		case B_AUTOVAC_LAUNCHER:
 			backendDesc = "autovacuum launcher";
 			break;
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7a92dac525..ee41d7009e 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -146,7 +146,8 @@
 #define BACKEND_TYPE_AUTOVAC	0x0002	/* autovacuum worker process */
 #define BACKEND_TYPE_WALSND		0x0004	/* walsender process */
 #define BACKEND_TYPE_BGWORKER	0x0008	/* bgworker process */
-#define BACKEND_TYPE_ALL		0x000F	/* OR of all the above */
+#define BACKEND_TYPE_ARCHIVER	0x0010	/* archiver process */
+#define BACKEND_TYPE_ALL		0x001F	/* OR of all the above */
 
 #define BACKEND_TYPE_WORKER		(BACKEND_TYPE_AUTOVAC | BACKEND_TYPE_BGWORKER)
 
@@ -539,6 +540,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1785,7 +1787,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3042,7 +3044,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3177,20 +3179,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3438,7 +3436,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3643,6 +3641,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3915,6 +3925,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5190,7 +5201,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5475,6 +5486,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 62d64aa0a1..dc7dd1c164 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -397,6 +397,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -409,6 +410,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 36b530bc27..0334213b98 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -718,6 +718,7 @@ typedef struct PgStat_GlobalStats
  */
 typedef enum BackendType
 {
+	B_ARCHIVER,
 	B_AUTOVAC_LAUNCHER,
 	B_AUTOVAC_WORKER,
 	B_BACKEND,
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index b3200874ca..e3ffc63f14 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
-- 
2.23.0


----Next_Part(Wed_Jan_22_17_24_04_2020_620)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v25 4/8] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/bootstrap/bootstrap.c   | 22 +++++----
 src/backend/postmaster/pgarch.c     | 75 +----------------------------
 src/backend/postmaster/postmaster.c | 43 +++++++++++------
 src/include/miscadmin.h             |  2 +
 src/include/postmaster/pgarch.h     |  4 +-
 5 files changed, 46 insertions(+), 100 deletions(-)

diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 5480a024e0..d398ce6f03 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -319,6 +319,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -439,30 +442,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index 37be0e2bbb..4971b3ae42 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -78,7 +78,6 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
@@ -95,7 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
 static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
@@ -110,75 +108,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -218,8 +147,8 @@ pgarch_forkexec(void)
  *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
  *	since we don't use 'em, it hardly matters...
  */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 2b9ab32293..cab7fb5381 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -146,7 +146,8 @@
 #define BACKEND_TYPE_AUTOVAC	0x0002	/* autovacuum worker process */
 #define BACKEND_TYPE_WALSND		0x0004	/* walsender process */
 #define BACKEND_TYPE_BGWORKER	0x0008	/* bgworker process */
-#define BACKEND_TYPE_ALL		0x000F	/* OR of all the above */
+#define BACKEND_TYPE_ARCHIVER	0x0010	/* archiver process */
+#define BACKEND_TYPE_ALL		0x001F	/* OR of all the above */
 
 #define BACKEND_TYPE_WORKER		(BACKEND_TYPE_AUTOVAC | BACKEND_TYPE_BGWORKER)
 
@@ -539,6 +540,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1785,7 +1787,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3055,7 +3057,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3190,20 +3192,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3451,7 +3449,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3656,6 +3654,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3928,6 +3938,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5208,7 +5219,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5493,6 +5504,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 14fa127ab1..619b2f9c71 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index b3200874ca..e3ffc63f14 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
-- 
2.18.2


----Next_Part(Thu_Mar_19_20_30_04_2020_284)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v25-0005-Use-latch-instead-of-SIGUSR1-to-wake-up-archiver.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v48 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..22e1cd244c 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3403,7 +3400,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3912,6 +3921,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..491747c113 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v49 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v50 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v51 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 194 ++++-------------------
 src/backend/postmaster/postmaster.c      |  83 +++++-----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 94 insertions(+), 236 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c219780c60 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,13 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,148 +75,29 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	ProcGlobal->archiverLatch = NULL;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..fd509869aa 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving of remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d71700a565 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -350,6 +350,8 @@ typedef struct PROC_HDR
 	Latch	   *walwriterLatch;
 	/* Checkpointer process's latch */
 	Latch	   *checkpointerLatch;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 	/* Current shared estimate of appropriate spins_per_delay value */
 	int			spins_per_delay;
 	/* The proc of the Startup process, since not in ProcArray */
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v52 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 224 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  83 ++++-----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 9 files changed, 139 insertions(+), 222 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..2558bcfb08 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,13 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c399e6c267 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,68 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	*latch;		/* latch to wake the archiver up */
+	slock_t  mutex;		/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size	size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool	found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver ", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	*latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +210,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +248,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +270,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..34c8551288 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v45 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index db0cfaa360..aabf9d73eb 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 0786fcf103..430d438303 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -354,6 +354,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Jan__8_10_24_34_2021_185)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v45-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v46 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index c87ffc6549..a1e51c5b99 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 0786fcf103..430d438303 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -354,6 +354,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Thu_Jan_14_15_14_25_2021_903)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v46-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v47 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index c87ffc6549..a1e51c5b99 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 683ab64f76..6cdaf3753d 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -355,6 +355,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Thu_Jan_21_12_03_48_2021_284)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v47-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v48 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..22e1cd244c 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3403,7 +3400,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3912,6 +3921,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..491747c113 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v49 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v50 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v51 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 194 ++++-------------------
 src/backend/postmaster/postmaster.c      |  83 +++++-----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 94 insertions(+), 236 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c219780c60 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,13 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,148 +75,29 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	ProcGlobal->archiverLatch = NULL;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..fd509869aa 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving of remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d71700a565 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -350,6 +350,8 @@ typedef struct PROC_HDR
 	Latch	   *walwriterLatch;
 	/* Checkpointer process's latch */
 	Latch	   *checkpointerLatch;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 	/* Current shared estimate of appropriate spins_per_delay value */
 	int			spins_per_delay;
 	/* The proc of the Startup process, since not in ProcArray */
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v52 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 224 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  83 ++++-----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 9 files changed, 139 insertions(+), 222 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..2558bcfb08 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,13 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c399e6c267 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,68 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	*latch;		/* latch to wake the archiver up */
+	slock_t  mutex;		/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size	size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool	found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver ", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	*latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +210,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +248,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +270,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..34c8551288 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v45 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index db0cfaa360..aabf9d73eb 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 0786fcf103..430d438303 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -354,6 +354,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Jan__8_10_24_34_2021_185)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v45-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v46 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index c87ffc6549..a1e51c5b99 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 0786fcf103..430d438303 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -354,6 +354,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Thu_Jan_14_15_14_25_2021_903)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v46-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v47 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index c87ffc6549..a1e51c5b99 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 683ab64f76..6cdaf3753d 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -355,6 +355,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Thu_Jan_21_12_03_48_2021_284)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v47-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v48 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..22e1cd244c 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3403,7 +3400,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3912,6 +3921,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..491747c113 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v49 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v50 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v51 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 194 ++++-------------------
 src/backend/postmaster/postmaster.c      |  83 +++++-----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 94 insertions(+), 236 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c219780c60 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,13 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,148 +75,29 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	ProcGlobal->archiverLatch = NULL;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..fd509869aa 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving of remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d71700a565 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -350,6 +350,8 @@ typedef struct PROC_HDR
 	Latch	   *walwriterLatch;
 	/* Checkpointer process's latch */
 	Latch	   *checkpointerLatch;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 	/* Current shared estimate of appropriate spins_per_delay value */
 	int			spins_per_delay;
 	/* The proc of the Startup process, since not in ProcArray */
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v52 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 224 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  83 ++++-----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 9 files changed, 139 insertions(+), 222 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..2558bcfb08 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,13 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c399e6c267 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,68 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	*latch;		/* latch to wake the archiver up */
+	slock_t  mutex;		/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size	size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool	found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver ", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	*latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +210,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +248,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +270,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..34c8551288 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v45 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index db0cfaa360..aabf9d73eb 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 0786fcf103..430d438303 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -354,6 +354,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Jan__8_10_24_34_2021_185)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v45-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v46 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index c87ffc6549..a1e51c5b99 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 0786fcf103..430d438303 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -354,6 +354,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Thu_Jan_14_15_14_25_2021_903)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v46-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v47 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index c87ffc6549..a1e51c5b99 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 683ab64f76..6cdaf3753d 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -355,6 +355,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Thu_Jan_21_12_03_48_2021_284)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v47-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v48 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..22e1cd244c 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3403,7 +3400,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3912,6 +3921,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..491747c113 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v49 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v50 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v51 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 194 ++++-------------------
 src/backend/postmaster/postmaster.c      |  83 +++++-----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 94 insertions(+), 236 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c219780c60 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,13 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,148 +75,29 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	ProcGlobal->archiverLatch = NULL;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..fd509869aa 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving of remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d71700a565 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -350,6 +350,8 @@ typedef struct PROC_HDR
 	Latch	   *walwriterLatch;
 	/* Checkpointer process's latch */
 	Latch	   *checkpointerLatch;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 	/* Current shared estimate of appropriate spins_per_delay value */
 	int			spins_per_delay;
 	/* The proc of the Startup process, since not in ProcArray */
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v52 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 224 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  83 ++++-----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 9 files changed, 139 insertions(+), 222 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..2558bcfb08 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,13 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c399e6c267 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,68 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	*latch;		/* latch to wake the archiver up */
+	slock_t  mutex;		/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size	size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool	found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver ", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	*latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +210,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +248,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +270,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..34c8551288 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v45 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index db0cfaa360..aabf9d73eb 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 0786fcf103..430d438303 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -354,6 +354,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Jan__8_10_24_34_2021_185)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v45-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v46 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index c87ffc6549..a1e51c5b99 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 0786fcf103..430d438303 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -354,6 +354,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Thu_Jan_14_15_14_25_2021_903)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v46-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v47 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index c87ffc6549..a1e51c5b99 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 683ab64f76..6cdaf3753d 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -355,6 +355,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Thu_Jan_21_12_03_48_2021_284)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v47-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v48 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..22e1cd244c 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3403,7 +3400,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3912,6 +3921,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..491747c113 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v49 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v50 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v51 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 194 ++++-------------------
 src/backend/postmaster/postmaster.c      |  83 +++++-----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 94 insertions(+), 236 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c219780c60 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,13 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,148 +75,29 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	ProcGlobal->archiverLatch = NULL;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..fd509869aa 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving of remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d71700a565 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -350,6 +350,8 @@ typedef struct PROC_HDR
 	Latch	   *walwriterLatch;
 	/* Checkpointer process's latch */
 	Latch	   *checkpointerLatch;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 	/* Current shared estimate of appropriate spins_per_delay value */
 	int			spins_per_delay;
 	/* The proc of the Startup process, since not in ProcArray */
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v52 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 224 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  83 ++++-----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 9 files changed, 139 insertions(+), 222 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..2558bcfb08 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,13 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c399e6c267 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,68 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	*latch;		/* latch to wake the archiver up */
+	slock_t  mutex;		/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size	size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool	found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver ", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	*latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +210,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +248,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +270,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..34c8551288 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v45 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index db0cfaa360..aabf9d73eb 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 0786fcf103..430d438303 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -354,6 +354,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Jan__8_10_24_34_2021_185)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v45-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v46 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index c87ffc6549..a1e51c5b99 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 0786fcf103..430d438303 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -354,6 +354,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Thu_Jan_14_15_14_25_2021_903)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v46-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v47 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index c87ffc6549..a1e51c5b99 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 683ab64f76..6cdaf3753d 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -355,6 +355,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Thu_Jan_21_12_03_48_2021_284)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v47-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v48 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..22e1cd244c 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3403,7 +3400,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3912,6 +3921,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..491747c113 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v49 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v50 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v51 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 194 ++++-------------------
 src/backend/postmaster/postmaster.c      |  83 +++++-----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 94 insertions(+), 236 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c219780c60 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,13 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,148 +75,29 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	ProcGlobal->archiverLatch = NULL;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..fd509869aa 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving of remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d71700a565 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -350,6 +350,8 @@ typedef struct PROC_HDR
 	Latch	   *walwriterLatch;
 	/* Checkpointer process's latch */
 	Latch	   *checkpointerLatch;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 	/* Current shared estimate of appropriate spins_per_delay value */
 	int			spins_per_delay;
 	/* The proc of the Startup process, since not in ProcArray */
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v52 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 224 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  83 ++++-----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 9 files changed, 139 insertions(+), 222 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..2558bcfb08 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,13 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c399e6c267 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,68 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	*latch;		/* latch to wake the archiver up */
+	slock_t  mutex;		/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size	size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool	found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver ", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	*latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +210,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +248,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +270,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..34c8551288 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v45 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index db0cfaa360..aabf9d73eb 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 0786fcf103..430d438303 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -354,6 +354,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Jan__8_10_24_34_2021_185)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v45-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v46 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index c87ffc6549..a1e51c5b99 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 0786fcf103..430d438303 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -354,6 +354,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Thu_Jan_14_15_14_25_2021_903)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v46-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v47 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index c87ffc6549..a1e51c5b99 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 683ab64f76..6cdaf3753d 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -355,6 +355,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Thu_Jan_21_12_03_48_2021_284)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v47-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v48 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..22e1cd244c 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3403,7 +3400,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3912,6 +3921,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..491747c113 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v49 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v50 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v51 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 194 ++++-------------------
 src/backend/postmaster/postmaster.c      |  83 +++++-----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 94 insertions(+), 236 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c219780c60 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,13 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,148 +75,29 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	ProcGlobal->archiverLatch = NULL;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..fd509869aa 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving of remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d71700a565 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -350,6 +350,8 @@ typedef struct PROC_HDR
 	Latch	   *walwriterLatch;
 	/* Checkpointer process's latch */
 	Latch	   *checkpointerLatch;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 	/* Current shared estimate of appropriate spins_per_delay value */
 	int			spins_per_delay;
 	/* The proc of the Startup process, since not in ProcArray */
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v52 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 224 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  83 ++++-----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 9 files changed, 139 insertions(+), 222 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..2558bcfb08 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,13 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c399e6c267 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,68 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	*latch;		/* latch to wake the archiver up */
+	slock_t  mutex;		/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size	size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool	found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver ", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	*latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +210,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +248,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +270,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..34c8551288 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v45 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index db0cfaa360..aabf9d73eb 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 0786fcf103..430d438303 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -354,6 +354,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Jan__8_10_24_34_2021_185)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v45-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v46 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index c87ffc6549..a1e51c5b99 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 0786fcf103..430d438303 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -354,6 +354,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Thu_Jan_14_15_14_25_2021_903)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v46-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v47 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index c87ffc6549..a1e51c5b99 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 683ab64f76..6cdaf3753d 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -355,6 +355,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Thu_Jan_21_12_03_48_2021_284)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v47-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v48 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..22e1cd244c 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3403,7 +3400,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3912,6 +3921,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..491747c113 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v49 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v50 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v51 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 194 ++++-------------------
 src/backend/postmaster/postmaster.c      |  83 +++++-----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 94 insertions(+), 236 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c219780c60 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,13 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,148 +75,29 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	ProcGlobal->archiverLatch = NULL;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..fd509869aa 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving of remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d71700a565 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -350,6 +350,8 @@ typedef struct PROC_HDR
 	Latch	   *walwriterLatch;
 	/* Checkpointer process's latch */
 	Latch	   *checkpointerLatch;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 	/* Current shared estimate of appropriate spins_per_delay value */
 	int			spins_per_delay;
 	/* The proc of the Startup process, since not in ProcArray */
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v52 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 224 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  83 ++++-----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 9 files changed, 139 insertions(+), 222 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..2558bcfb08 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,13 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c399e6c267 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,68 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	*latch;		/* latch to wake the archiver up */
+	slock_t  mutex;		/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size	size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool	found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver ", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	*latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +210,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +248,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +270,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..34c8551288 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v33 4/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index cdd586fcfb..ee3444284b 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -489,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 5480a024e0..d398ce6f03 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -319,6 +319,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -439,30 +442,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index 37be0e2bbb..063d1323ea 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	pqsignal(SIGQUIT, SignalHandlerForCrashExit);
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 160afe9f39..9de9396628 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -539,6 +539,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1785,7 +1786,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3068,7 +3069,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3203,20 +3204,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3464,7 +3461,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3669,6 +3666,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3941,6 +3950,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5216,7 +5226,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5259,16 +5269,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5501,6 +5501,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 5aa19d3f78..7acc48734e 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -187,6 +187,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index e917dfe92d..0783692c83 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -336,6 +336,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 1c67de2ede..54ce0b97d7 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 14fa127ab1..619b2f9c71 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index b3200874ca..e3ffc63f14 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index 56c5ec4481..c691acf8cd 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index ae4f573ab4..1a8a0c2e15 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -272,6 +272,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.18.2


----Next_Part(Fri_May_15_17_30_36_2020_111)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v33-0005-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v45 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index db0cfaa360..aabf9d73eb 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 0786fcf103..430d438303 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -354,6 +354,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Jan__8_10_24_34_2021_185)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v45-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v46 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index c87ffc6549..a1e51c5b99 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 0786fcf103..430d438303 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -354,6 +354,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Thu_Jan_14_15_14_25_2021_903)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v46-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v47 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index c87ffc6549..a1e51c5b99 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 683ab64f76..6cdaf3753d 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -355,6 +355,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Thu_Jan_21_12_03_48_2021_284)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v47-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v48 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..22e1cd244c 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3403,7 +3400,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3912,6 +3921,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..491747c113 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v49 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v50 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v51 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 194 ++++-------------------
 src/backend/postmaster/postmaster.c      |  83 +++++-----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 94 insertions(+), 236 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c219780c60 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,13 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,148 +75,29 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	ProcGlobal->archiverLatch = NULL;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..fd509869aa 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving of remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d71700a565 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -350,6 +350,8 @@ typedef struct PROC_HDR
 	Latch	   *walwriterLatch;
 	/* Checkpointer process's latch */
 	Latch	   *checkpointerLatch;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 	/* Current shared estimate of appropriate spins_per_delay value */
 	int			spins_per_delay;
 	/* The proc of the Startup process, since not in ProcArray */
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v52 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 224 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  83 ++++-----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 9 files changed, 139 insertions(+), 222 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..2558bcfb08 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,13 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c399e6c267 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,68 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	*latch;		/* latch to wake the archiver up */
+	slock_t  mutex;		/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size	size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool	found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver ", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	*latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +210,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +248,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +270,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..34c8551288 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v48 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..22e1cd244c 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3403,7 +3400,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3912,6 +3921,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..491747c113 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v49 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v50 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v51 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 194 ++++-------------------
 src/backend/postmaster/postmaster.c      |  83 +++++-----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 94 insertions(+), 236 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c219780c60 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,13 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,148 +75,29 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	ProcGlobal->archiverLatch = NULL;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..fd509869aa 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving of remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d71700a565 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -350,6 +350,8 @@ typedef struct PROC_HDR
 	Latch	   *walwriterLatch;
 	/* Checkpointer process's latch */
 	Latch	   *checkpointerLatch;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 	/* Current shared estimate of appropriate spins_per_delay value */
 	int			spins_per_delay;
 	/* The proc of the Startup process, since not in ProcArray */
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v52 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 224 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  83 ++++-----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 9 files changed, 139 insertions(+), 222 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..2558bcfb08 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,13 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c399e6c267 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,68 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	*latch;		/* latch to wake the archiver up */
+	slock_t  mutex;		/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size	size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool	found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver ", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	*latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +210,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +248,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +270,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..34c8551288 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v29 4/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlog.c        |  46 ++++++++++
 src/backend/access/transam/xlogarchive.c |   2 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++---
 src/backend/postmaster/pgarch.c          | 102 ++++-------------------
 src/backend/postmaster/postmaster.c      |  53 ++++++------
 src/include/access/xlog.h                |   2 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 10 files changed, 108 insertions(+), 127 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 977d448f50..d75a257da2 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -684,6 +684,13 @@ typedef struct XLogCtlData
 	 */
 	Latch		recoveryWakeupLatch;
 
+	/*
+	 * archiverWakeupLatch is used to wake up the archiver process to process
+	 * completed WAL segments, if it is waiting for WAL to arrive.  Protected
+	 * by info_lck.
+	 */
+	Latch	   *archiverWakeupLatch;
+
 	/*
 	 * During recovery, we keep a copy of the latest checkpoint record here.
 	 * lastCheckPointRecPtr points to start of checkpoint record and
@@ -8450,6 +8457,45 @@ GetLastSegSwitchData(XLogRecPtr *lastSwitchLSN)
 	return result;
 }
 
+/*
+ * XLogArchiveWakeupStart - Set up archiver wakeup stuff
+ */
+void
+XLogArchiveWakeupStart(void)
+{
+	SpinLockAcquire(&XLogCtl->info_lck);
+	Assert(XLogCtl->archiverWakeupLatch == NULL);
+	XLogCtl->archiverWakeupLatch = MyLatch;
+	SpinLockRelease(&XLogCtl->info_lck);
+}
+
+/*
+ * XLogArchiveWakeupEnd - Clean up archiver wakeup stuff
+ */
+void
+XLogArchiveWakeupEnd(void)
+{
+	SpinLockAcquire(&XLogCtl->info_lck);
+	XLogCtl->archiverWakeupLatch = NULL;
+	SpinLockRelease(&XLogCtl->info_lck);
+}
+
+/*
+ * XLogWakeupArchiver - Wake up archiver process
+ */
+void
+XLogArchiveWakeup(void)
+{
+	Latch *latch;
+
+	SpinLockAcquire(&XLogCtl->info_lck);
+	latch = XLogCtl->archiverWakeupLatch;
+	SpinLockRelease(&XLogCtl->info_lck);
+
+	if (latch)
+		SetLatch(latch);
+}
+
 /*
  * This must be called ONCE during postmaster or standalone-backend shutdown
  */
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index d62c12310a..d6c8bcce8b 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -490,7 +490,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		XLogArchiveWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 5480a024e0..d398ce6f03 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -319,6 +319,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -439,30 +442,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index 37be0e2bbb..6fe7a136ba 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,7 +79,6 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
@@ -95,8 +95,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +108,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +141,21 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
+/* Clean up notification stuff on exit */
+static void
+PgArchiverKill(int code, Datum arg)
+{
+	XLogArchiveWakeupEnd();
+}
+
 /*
  * PgArchiverMain
  *
  *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
  *	since we don't use 'em, it hardly matters...
  */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,7 +167,7 @@ PgArchiverMain(int argc, char *argv[])
 	pqsignal(SIGQUIT, SignalHandlerForCrashExit);
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
@@ -240,24 +176,14 @@ PgArchiverMain(int argc, char *argv[])
 	MyBackendType = B_ARCHIVER;
 	init_ps_display(NULL);
 
+	XLogArchiveWakeupStart();
+	on_shmem_exit(PgArchiverKill, 0);
+	
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 73d278f3b2..a4b9d212a2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -146,7 +146,8 @@
 #define BACKEND_TYPE_AUTOVAC	0x0002	/* autovacuum worker process */
 #define BACKEND_TYPE_WALSND		0x0004	/* walsender process */
 #define BACKEND_TYPE_BGWORKER	0x0008	/* bgworker process */
-#define BACKEND_TYPE_ALL		0x000F	/* OR of all the above */
+#define BACKEND_TYPE_ARCHIVER	0x0010	/* archiver process */
+#define BACKEND_TYPE_ALL		0x001F	/* OR of all the above */
 
 #define BACKEND_TYPE_WORKER		(BACKEND_TYPE_AUTOVAC | BACKEND_TYPE_BGWORKER)
 
@@ -539,6 +540,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1785,7 +1787,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3055,7 +3057,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3190,20 +3192,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3451,7 +3449,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3656,6 +3654,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3928,6 +3938,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5208,7 +5219,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5251,16 +5262,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5493,6 +5494,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 9ec7b31cce..c0e149d526 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -313,6 +313,8 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 1c67de2ede..54ce0b97d7 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 14fa127ab1..619b2f9c71 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index b3200874ca..e3ffc63f14 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index 56c5ec4481..c691acf8cd 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
-- 
2.18.2


----Next_Part(Wed_Apr__1_15_15_11_2020_923)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v29-0005-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v30 4/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlog.c        |  46 +++++++++
 src/backend/access/transam/xlogarchive.c |   2 +-
 src/backend/bootstrap/bootstrap.c        |  22 +++--
 src/backend/postmaster/pgarch.c          | 115 ++++-------------------
 src/backend/postmaster/postmaster.c      |  53 ++++++-----
 src/include/access/xlog.h                |   2 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 10 files changed, 112 insertions(+), 136 deletions(-)

diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index 977d448f50..d75a257da2 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -684,6 +684,13 @@ typedef struct XLogCtlData
 	 */
 	Latch		recoveryWakeupLatch;
 
+	/*
+	 * archiverWakeupLatch is used to wake up the archiver process to process
+	 * completed WAL segments, if it is waiting for WAL to arrive.  Protected
+	 * by info_lck.
+	 */
+	Latch	   *archiverWakeupLatch;
+
 	/*
 	 * During recovery, we keep a copy of the latest checkpoint record here.
 	 * lastCheckPointRecPtr points to start of checkpoint record and
@@ -8450,6 +8457,45 @@ GetLastSegSwitchData(XLogRecPtr *lastSwitchLSN)
 	return result;
 }
 
+/*
+ * XLogArchiveWakeupStart - Set up archiver wakeup stuff
+ */
+void
+XLogArchiveWakeupStart(void)
+{
+	SpinLockAcquire(&XLogCtl->info_lck);
+	Assert(XLogCtl->archiverWakeupLatch == NULL);
+	XLogCtl->archiverWakeupLatch = MyLatch;
+	SpinLockRelease(&XLogCtl->info_lck);
+}
+
+/*
+ * XLogArchiveWakeupEnd - Clean up archiver wakeup stuff
+ */
+void
+XLogArchiveWakeupEnd(void)
+{
+	SpinLockAcquire(&XLogCtl->info_lck);
+	XLogCtl->archiverWakeupLatch = NULL;
+	SpinLockRelease(&XLogCtl->info_lck);
+}
+
+/*
+ * XLogWakeupArchiver - Wake up archiver process
+ */
+void
+XLogArchiveWakeup(void)
+{
+	Latch *latch;
+
+	SpinLockAcquire(&XLogCtl->info_lck);
+	latch = XLogCtl->archiverWakeupLatch;
+	SpinLockRelease(&XLogCtl->info_lck);
+
+	if (latch)
+		SetLatch(latch);
+}
+
 /*
  * This must be called ONCE during postmaster or standalone-backend shutdown
  */
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index d62c12310a..d6c8bcce8b 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -490,7 +490,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		XLogArchiveWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 5480a024e0..d398ce6f03 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -319,6 +319,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -439,30 +442,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index 37be0e2bbb..7b66cb5613 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,7 +79,6 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
@@ -95,8 +95,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +108,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +141,16 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Clean up notification stuff on exit */
+static void
+PgArchiverKill(int code, Datum arg)
+{
+	XLogArchiveWakeupEnd();
+}
+
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +162,23 @@ PgArchiverMain(int argc, char *argv[])
 	pqsignal(SIGQUIT, SignalHandlerForCrashExit);
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
-
+	XLogArchiveWakeupStart();
+	on_shmem_exit(PgArchiverKill, 0);
+	
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 73d278f3b2..a4b9d212a2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -146,7 +146,8 @@
 #define BACKEND_TYPE_AUTOVAC	0x0002	/* autovacuum worker process */
 #define BACKEND_TYPE_WALSND		0x0004	/* walsender process */
 #define BACKEND_TYPE_BGWORKER	0x0008	/* bgworker process */
-#define BACKEND_TYPE_ALL		0x000F	/* OR of all the above */
+#define BACKEND_TYPE_ARCHIVER	0x0010	/* archiver process */
+#define BACKEND_TYPE_ALL		0x001F	/* OR of all the above */
 
 #define BACKEND_TYPE_WORKER		(BACKEND_TYPE_AUTOVAC | BACKEND_TYPE_BGWORKER)
 
@@ -539,6 +540,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1785,7 +1787,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3055,7 +3057,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3190,20 +3192,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3451,7 +3449,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3656,6 +3654,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3928,6 +3938,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5208,7 +5219,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5251,16 +5262,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5493,6 +5494,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 9ec7b31cce..c0e149d526 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -313,6 +313,8 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 1c67de2ede..54ce0b97d7 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 14fa127ab1..619b2f9c71 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index b3200874ca..e3ffc63f14 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index 56c5ec4481..c691acf8cd 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
-- 
2.18.2


----Next_Part(Wed_Apr__1_17_37_23_2020_570)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v30-0005-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v31 4/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index d62c12310a..2f8672ac0c 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -489,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 5480a024e0..d398ce6f03 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -319,6 +319,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -439,30 +442,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index 37be0e2bbb..063d1323ea 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	pqsignal(SIGQUIT, SignalHandlerForCrashExit);
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 73d278f3b2..e97995f973 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -539,6 +539,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1785,7 +1786,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3055,7 +3056,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3190,20 +3191,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3451,7 +3448,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3656,6 +3653,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3928,6 +3937,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5208,7 +5218,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5251,16 +5261,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5493,6 +5493,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 9938cddb57..af4599bd82 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -187,6 +187,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 9ec7b31cce..4435df82b6 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -313,6 +313,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 1c67de2ede..54ce0b97d7 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 14fa127ab1..619b2f9c71 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index b3200874ca..e3ffc63f14 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index 56c5ec4481..c691acf8cd 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index d21780108b..a87e7dc711 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -272,6 +272,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.18.2


----Next_Part(Fri_Apr__3_17_31_17_2020_104)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v31-0005-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v32 4/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index d62c12310a..2f8672ac0c 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -489,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 5480a024e0..d398ce6f03 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -319,6 +319,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -439,30 +442,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index 37be0e2bbb..063d1323ea 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	pqsignal(SIGQUIT, SignalHandlerForCrashExit);
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 73d278f3b2..e97995f973 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -539,6 +539,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1785,7 +1786,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3055,7 +3056,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3190,20 +3191,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3451,7 +3448,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3656,6 +3653,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3928,6 +3937,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5208,7 +5218,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5251,16 +5261,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5493,6 +5493,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 9938cddb57..af4599bd82 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -187,6 +187,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 9ec7b31cce..4435df82b6 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -313,6 +313,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 1c67de2ede..54ce0b97d7 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 14fa127ab1..619b2f9c71 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index b3200874ca..e3ffc63f14 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index 56c5ec4481..c691acf8cd 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index d21780108b..a87e7dc711 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -272,6 +272,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.18.2


----Next_Part(Tue_Apr__7_16_38_17_2020_299)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v32-0005-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v33 4/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 55becd65d4..2417de72a0 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -489,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 5480a024e0..d398ce6f03 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -319,6 +319,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -439,30 +442,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index 37be0e2bbb..063d1323ea 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	pqsignal(SIGQUIT, SignalHandlerForCrashExit);
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 0578e92ba9..2687d2af47 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -539,6 +539,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1785,7 +1786,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3055,7 +3056,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3190,20 +3191,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3451,7 +3448,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3656,6 +3653,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3928,6 +3937,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5203,7 +5213,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5246,16 +5256,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5488,6 +5488,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 5aa19d3f78..7acc48734e 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -187,6 +187,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 0a12afb59e..099da8cd76 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -336,6 +336,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 1c67de2ede..54ce0b97d7 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 14fa127ab1..619b2f9c71 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index b3200874ca..e3ffc63f14 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index 56c5ec4481..c691acf8cd 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index ae4f573ab4..1a8a0c2e15 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -272,6 +272,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.18.2


----Next_Part(Thu_Apr_30_13_22_05_2020_409)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v33-0005-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v48 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..22e1cd244c 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3403,7 +3400,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3912,6 +3921,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..491747c113 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v49 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v50 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v51 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 194 ++++-------------------
 src/backend/postmaster/postmaster.c      |  83 +++++-----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 94 insertions(+), 236 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c219780c60 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,13 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,148 +75,29 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	ProcGlobal->archiverLatch = NULL;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..fd509869aa 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving of remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d71700a565 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -350,6 +350,8 @@ typedef struct PROC_HDR
 	Latch	   *walwriterLatch;
 	/* Checkpointer process's latch */
 	Latch	   *checkpointerLatch;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 	/* Current shared estimate of appropriate spins_per_delay value */
 	int			spins_per_delay;
 	/* The proc of the Startup process, since not in ProcArray */
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v52 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 224 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  83 ++++-----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 9 files changed, 139 insertions(+), 222 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..2558bcfb08 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,13 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c399e6c267 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,68 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	*latch;		/* latch to wake the archiver up */
+	slock_t  mutex;		/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size	size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool	found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver ", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	*latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +210,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +248,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +270,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..34c8551288 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v43 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index f39dc4ddf1..d69e20961d 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index a7ed93fdc1..edda899554 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index ed1b65358d..e3a520def9 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 5d09822c81..8a4706a870 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -547,6 +547,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1787,7 +1788,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3041,7 +3042,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3176,20 +3177,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3437,7 +3434,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3642,6 +3639,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3938,6 +3947,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5185,7 +5195,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5230,16 +5240,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5481,6 +5481,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 7dc3911590..fc23539137 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -181,6 +181,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 221af87e71..65443063e8 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 1c67de2ede..54ce0b97d7 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 72e3352398..bba002ad24 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -418,6 +418,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -430,6 +431,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index b3200874ca..e3ffc63f14 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index 56c5ec4481..c691acf8cd 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index e77f76ae8a..a656910d02 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -354,6 +354,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Dec_11_16_50_03_2020_915)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v43-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v44 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index f39dc4ddf1..d69e20961d 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index a7ed93fdc1..edda899554 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index ed1b65358d..e3a520def9 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 5d09822c81..8a4706a870 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -547,6 +547,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1787,7 +1788,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3041,7 +3042,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3176,20 +3177,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3437,7 +3434,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3642,6 +3639,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3938,6 +3947,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5185,7 +5195,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5230,16 +5240,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5481,6 +5481,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 7dc3911590..fc23539137 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -181,6 +181,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 221af87e71..65443063e8 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 1c67de2ede..54ce0b97d7 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 72e3352398..bba002ad24 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -418,6 +418,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -430,6 +431,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index b3200874ca..e3ffc63f14 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index 56c5ec4481..c691acf8cd 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index e77f76ae8a..a656910d02 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -354,6 +354,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Mon_Dec_21_17_16_20_2020_608)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v44-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v45 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index db0cfaa360..aabf9d73eb 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 0786fcf103..430d438303 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -354,6 +354,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Jan__8_10_24_34_2021_185)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v45-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v46 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index c87ffc6549..a1e51c5b99 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 0786fcf103..430d438303 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -354,6 +354,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Thu_Jan_14_15_14_25_2021_903)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v46-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v47 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index c87ffc6549..a1e51c5b99 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 683ab64f76..6cdaf3753d 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -355,6 +355,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Thu_Jan_21_12_03_48_2021_284)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v47-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v48 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..22e1cd244c 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3403,7 +3400,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3912,6 +3921,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..491747c113 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v49 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v50 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v51 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 194 ++++-------------------
 src/backend/postmaster/postmaster.c      |  83 +++++-----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 94 insertions(+), 236 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c219780c60 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,13 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,148 +75,29 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	ProcGlobal->archiverLatch = NULL;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..fd509869aa 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving of remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d71700a565 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -350,6 +350,8 @@ typedef struct PROC_HDR
 	Latch	   *walwriterLatch;
 	/* Checkpointer process's latch */
 	Latch	   *checkpointerLatch;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 	/* Current shared estimate of appropriate spins_per_delay value */
 	int			spins_per_delay;
 	/* The proc of the Startup process, since not in ProcArray */
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v52 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 224 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  83 ++++-----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 9 files changed, 139 insertions(+), 222 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..2558bcfb08 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,13 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c399e6c267 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,68 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	*latch;		/* latch to wake the archiver up */
+	slock_t  mutex;		/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size	size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool	found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver ", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	*latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +210,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +248,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +270,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..34c8551288 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v36 4/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 8f8734dc1d..2e6c322142 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -489,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 76b2f5066f..81bfaea869 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index 37be0e2bbb..063d1323ea 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	pqsignal(SIGQUIT, SignalHandlerForCrashExit);
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 42223c0f61..4c296dd214 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -554,6 +554,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1799,7 +1800,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3051,7 +3052,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3186,20 +3187,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3447,7 +3444,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3652,6 +3649,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3948,6 +3957,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5223,7 +5233,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5268,16 +5278,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5515,6 +5515,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index aa9fbd8054..9cc5226667 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -181,6 +181,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 221af87e71..65443063e8 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 1c67de2ede..54ce0b97d7 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 72e3352398..bba002ad24 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -418,6 +418,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -430,6 +431,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index b3200874ca..e3ffc63f14 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index 56c5ec4481..c691acf8cd 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 9c9a50ae45..de20520b8c 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -345,6 +345,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.18.4


----Next_Part(Tue_Sep__8_17_55_57_2020_197)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v36-0005-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v37 3/6] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 8f8734dc1d..2e6c322142 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -489,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 76b2f5066f..81bfaea869 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index ed1b65358d..e3a520def9 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 959e3b8873..b811c961a6 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -555,6 +555,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1800,7 +1801,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3054,7 +3055,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3189,20 +3190,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3450,7 +3447,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3655,6 +3652,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3951,6 +3960,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5230,7 +5240,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5275,16 +5285,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5526,6 +5526,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 88566bd9fa..746bed773e 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -181,6 +181,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 221af87e71..65443063e8 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 1c67de2ede..54ce0b97d7 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 72e3352398..bba002ad24 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -418,6 +418,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -430,6 +431,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index b3200874ca..e3ffc63f14 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index 56c5ec4481..c691acf8cd 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 9c9a50ae45..de20520b8c 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -345,6 +345,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.18.4


----Next_Part(Fri_Sep_25_09_27_26_2020_419)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v37-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v38 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index cae93ab69d..6908bec2f9 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -489,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 76b2f5066f..81bfaea869 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index ed1b65358d..e3a520def9 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 959e3b8873..b811c961a6 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -555,6 +555,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1800,7 +1801,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3054,7 +3055,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3189,20 +3190,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3450,7 +3447,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3655,6 +3652,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3951,6 +3960,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5230,7 +5240,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5275,16 +5285,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5526,6 +5526,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 88566bd9fa..746bed773e 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -181,6 +181,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 221af87e71..65443063e8 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 1c67de2ede..54ce0b97d7 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 72e3352398..bba002ad24 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -418,6 +418,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -430,6 +431,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index b3200874ca..e3ffc63f14 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index 56c5ec4481..c691acf8cd 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 9c9a50ae45..de20520b8c 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -345,6 +345,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.18.4


----Next_Part(Thu_Oct__1_09_07_22_2020_252)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v38-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v39 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index cae93ab69d..6908bec2f9 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -489,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 76b2f5066f..81bfaea869 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index ed1b65358d..e3a520def9 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 959e3b8873..b811c961a6 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -555,6 +555,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1800,7 +1801,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3054,7 +3055,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3189,20 +3190,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3450,7 +3447,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3655,6 +3652,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3951,6 +3960,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5230,7 +5240,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5275,16 +5285,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5526,6 +5526,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 88566bd9fa..746bed773e 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -181,6 +181,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 221af87e71..65443063e8 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 1c67de2ede..54ce0b97d7 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 72e3352398..bba002ad24 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -418,6 +418,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -430,6 +431,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index b3200874ca..e3ffc63f14 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index 56c5ec4481..c691acf8cd 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 9c9a50ae45..de20520b8c 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -345,6 +345,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.18.4


----Next_Part(Tue_Oct__6_10_06_44_2020_382)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v39-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v40 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index cae93ab69d..6908bec2f9 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -489,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index a7ed93fdc1..edda899554 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index ed1b65358d..e3a520def9 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 959e3b8873..b811c961a6 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -555,6 +555,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1800,7 +1801,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3054,7 +3055,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3189,20 +3190,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3450,7 +3447,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3655,6 +3652,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3951,6 +3960,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5230,7 +5240,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5275,16 +5285,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5526,6 +5526,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 88566bd9fa..746bed773e 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -181,6 +181,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 221af87e71..65443063e8 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 1c67de2ede..54ce0b97d7 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 72e3352398..bba002ad24 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -418,6 +418,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -430,6 +431,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index b3200874ca..e3ffc63f14 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index 56c5ec4481..c691acf8cd 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 9c9a50ae45..de20520b8c 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -345,6 +345,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.18.4


----Next_Part(Wed_Nov__4_17_39_10_2020_208)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v40-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v41 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index cae93ab69d..6908bec2f9 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -489,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index a7ed93fdc1..edda899554 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index ed1b65358d..e3a520def9 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 959e3b8873..b811c961a6 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -555,6 +555,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1800,7 +1801,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3054,7 +3055,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3189,20 +3190,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3450,7 +3447,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3655,6 +3652,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3951,6 +3960,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5230,7 +5240,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5275,16 +5285,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5526,6 +5526,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 88566bd9fa..746bed773e 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -181,6 +181,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 221af87e71..65443063e8 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 1c67de2ede..54ce0b97d7 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 72e3352398..bba002ad24 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -418,6 +418,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -430,6 +431,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index b3200874ca..e3ffc63f14 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index 56c5ec4481..c691acf8cd 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 9c9a50ae45..de20520b8c 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -345,6 +345,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.18.4


----Next_Part(Fri_Nov__6_09_27_56_2020_738)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v41-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v42 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index cae93ab69d..6908bec2f9 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -489,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index a7ed93fdc1..edda899554 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index ed1b65358d..e3a520def9 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index b7799ed1d2..a1dd6964e9 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -547,6 +547,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1785,7 +1786,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3039,7 +3040,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3174,20 +3175,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3435,7 +3432,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3640,6 +3637,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3936,6 +3945,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5177,7 +5187,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5222,16 +5232,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5473,6 +5473,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 88566bd9fa..746bed773e 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -181,6 +181,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 221af87e71..65443063e8 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 1c67de2ede..54ce0b97d7 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 72e3352398..bba002ad24 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -418,6 +418,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -430,6 +431,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index b3200874ca..e3ffc63f14 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index 56c5ec4481..c691acf8cd 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 9c9a50ae45..de20520b8c 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -345,6 +345,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.18.4


----Next_Part(Wed_Nov_11_10_07_22_2020_796)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v42-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v45 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index db0cfaa360..aabf9d73eb 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 0786fcf103..430d438303 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -354,6 +354,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Jan__8_10_24_34_2021_185)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v45-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v46 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index c87ffc6549..a1e51c5b99 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 0786fcf103..430d438303 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -354,6 +354,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Thu_Jan_14_15_14_25_2021_903)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v46-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v47 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index c87ffc6549..a1e51c5b99 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 683ab64f76..6cdaf3753d 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -355,6 +355,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Thu_Jan_21_12_03_48_2021_284)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v47-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v48 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..22e1cd244c 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3403,7 +3400,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3912,6 +3921,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..491747c113 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v49 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v50 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v51 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 194 ++++-------------------
 src/backend/postmaster/postmaster.c      |  83 +++++-----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 94 insertions(+), 236 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c219780c60 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,13 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,148 +75,29 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	ProcGlobal->archiverLatch = NULL;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..fd509869aa 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving of remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d71700a565 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -350,6 +350,8 @@ typedef struct PROC_HDR
 	Latch	   *walwriterLatch;
 	/* Checkpointer process's latch */
 	Latch	   *checkpointerLatch;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 	/* Current shared estimate of appropriate spins_per_delay value */
 	int			spins_per_delay;
 	/* The proc of the Startup process, since not in ProcArray */
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v52 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 224 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  83 ++++-----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 9 files changed, 139 insertions(+), 222 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..2558bcfb08 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,13 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c399e6c267 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,68 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	*latch;		/* latch to wake the archiver up */
+	slock_t  mutex;		/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size	size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool	found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver ", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	*latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +210,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +248,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +270,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..34c8551288 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v34 4/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index cdd586fcfb..ee3444284b 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -489,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 5480a024e0..d398ce6f03 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -319,6 +319,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -439,30 +442,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index 37be0e2bbb..063d1323ea 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	pqsignal(SIGQUIT, SignalHandlerForCrashExit);
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 160afe9f39..9de9396628 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -539,6 +539,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1785,7 +1786,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3068,7 +3069,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3203,20 +3204,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3464,7 +3461,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3669,6 +3666,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3941,6 +3950,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5216,7 +5226,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5259,16 +5269,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5501,6 +5501,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index f5eef6fa4e..46f0198510 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -187,6 +187,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index e917dfe92d..0783692c83 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -336,6 +336,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 1c67de2ede..54ce0b97d7 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 14fa127ab1..619b2f9c71 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index b3200874ca..e3ffc63f14 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index 56c5ec4481..c691acf8cd 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 1ee9000b2b..8ab6d859bb 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -270,6 +270,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.18.2


----Next_Part(Mon_Jun__1_18_00_01_2020_089)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v34-0005-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v35 4/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index cdd586fcfb..ee3444284b 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -489,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 5480a024e0..d398ce6f03 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -319,6 +319,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -439,30 +442,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index 37be0e2bbb..063d1323ea 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	pqsignal(SIGQUIT, SignalHandlerForCrashExit);
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index b4d475bb0b..30f3fc6ba1 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -539,6 +539,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1785,7 +1786,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3068,7 +3069,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3203,20 +3204,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3464,7 +3461,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3669,6 +3666,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3941,6 +3950,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5216,7 +5226,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5259,16 +5269,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5501,6 +5501,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index f5eef6fa4e..46f0198510 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -187,6 +187,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index e917dfe92d..0783692c83 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -336,6 +336,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 1c67de2ede..54ce0b97d7 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 18bc8a7b90..cf0b463eba 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index b3200874ca..e3ffc63f14 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index 56c5ec4481..c691acf8cd 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 1ee9000b2b..8ab6d859bb 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -270,6 +270,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.18.2


----Next_Part(Mon_Jun__8_17_32_04_2020_489)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v35-0005-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v45 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index db0cfaa360..aabf9d73eb 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 0786fcf103..430d438303 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -354,6 +354,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Jan__8_10_24_34_2021_185)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v45-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v46 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index c87ffc6549..a1e51c5b99 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 0786fcf103..430d438303 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -354,6 +354,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Thu_Jan_14_15_14_25_2021_903)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v46-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v47 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index c87ffc6549..a1e51c5b99 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 683ab64f76..6cdaf3753d 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -355,6 +355,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Thu_Jan_21_12_03_48_2021_284)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v47-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v48 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..22e1cd244c 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3403,7 +3400,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3912,6 +3921,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..491747c113 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v49 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v50 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v51 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 194 ++++-------------------
 src/backend/postmaster/postmaster.c      |  83 +++++-----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 94 insertions(+), 236 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c219780c60 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,13 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,148 +75,29 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	ProcGlobal->archiverLatch = NULL;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..fd509869aa 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving of remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d71700a565 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -350,6 +350,8 @@ typedef struct PROC_HDR
 	Latch	   *walwriterLatch;
 	/* Checkpointer process's latch */
 	Latch	   *checkpointerLatch;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 	/* Current shared estimate of appropriate spins_per_delay value */
 	int			spins_per_delay;
 	/* The proc of the Startup process, since not in ProcArray */
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v52 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 224 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  83 ++++-----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 9 files changed, 139 insertions(+), 222 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..2558bcfb08 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,13 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c399e6c267 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,68 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	*latch;		/* latch to wake the archiver up */
+	slock_t  mutex;		/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size	size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool	found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver ", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	*latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +210,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +248,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +270,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..34c8551288 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v45 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index db0cfaa360..aabf9d73eb 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 0786fcf103..430d438303 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -354,6 +354,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Jan__8_10_24_34_2021_185)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v45-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v46 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index c87ffc6549..a1e51c5b99 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 0786fcf103..430d438303 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -354,6 +354,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Thu_Jan_14_15_14_25_2021_903)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v46-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v47 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index c87ffc6549..a1e51c5b99 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 683ab64f76..6cdaf3753d 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -355,6 +355,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Thu_Jan_21_12_03_48_2021_284)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v47-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v48 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..22e1cd244c 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3403,7 +3400,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3912,6 +3921,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..491747c113 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v49 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v50 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v51 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 194 ++++-------------------
 src/backend/postmaster/postmaster.c      |  83 +++++-----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 94 insertions(+), 236 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c219780c60 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,13 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,148 +75,29 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	ProcGlobal->archiverLatch = NULL;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..fd509869aa 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving of remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d71700a565 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -350,6 +350,8 @@ typedef struct PROC_HDR
 	Latch	   *walwriterLatch;
 	/* Checkpointer process's latch */
 	Latch	   *checkpointerLatch;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 	/* Current shared estimate of appropriate spins_per_delay value */
 	int			spins_per_delay;
 	/* The proc of the Startup process, since not in ProcArray */
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v52 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 224 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  83 ++++-----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 9 files changed, 139 insertions(+), 222 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..2558bcfb08 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,13 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c399e6c267 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,68 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	*latch;		/* latch to wake the archiver up */
+	slock_t  mutex;		/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size	size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool	found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver ", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	*latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +210,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +248,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +270,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..34c8551288 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v45 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index db0cfaa360..aabf9d73eb 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 0786fcf103..430d438303 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -354,6 +354,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Jan__8_10_24_34_2021_185)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v45-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v46 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index c87ffc6549..a1e51c5b99 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 0786fcf103..430d438303 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -354,6 +354,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Thu_Jan_14_15_14_25_2021_903)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v46-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v47 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index c87ffc6549..a1e51c5b99 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 683ab64f76..6cdaf3753d 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -355,6 +355,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Thu_Jan_21_12_03_48_2021_284)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v47-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v48 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..22e1cd244c 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3403,7 +3400,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3912,6 +3921,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..491747c113 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v49 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v50 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v51 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 194 ++++-------------------
 src/backend/postmaster/postmaster.c      |  83 +++++-----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 94 insertions(+), 236 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c219780c60 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,13 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,148 +75,29 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	ProcGlobal->archiverLatch = NULL;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..fd509869aa 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving of remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d71700a565 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -350,6 +350,8 @@ typedef struct PROC_HDR
 	Latch	   *walwriterLatch;
 	/* Checkpointer process's latch */
 	Latch	   *checkpointerLatch;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 	/* Current shared estimate of appropriate spins_per_delay value */
 	int			spins_per_delay;
 	/* The proc of the Startup process, since not in ProcArray */
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v52 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 224 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  83 ++++-----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 9 files changed, 139 insertions(+), 222 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..2558bcfb08 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,13 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c399e6c267 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,68 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	*latch;		/* latch to wake the archiver up */
+	slock_t  mutex;		/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size	size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool	found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver ", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	*latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +210,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +248,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +270,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..34c8551288 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v45 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index db0cfaa360..aabf9d73eb 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 0786fcf103..430d438303 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -354,6 +354,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Jan__8_10_24_34_2021_185)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v45-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v46 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index c87ffc6549..a1e51c5b99 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 0786fcf103..430d438303 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -354,6 +354,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Thu_Jan_14_15_14_25_2021_903)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v46-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v47 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index c87ffc6549..a1e51c5b99 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 683ab64f76..6cdaf3753d 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -355,6 +355,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Thu_Jan_21_12_03_48_2021_284)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v47-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v48 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..22e1cd244c 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3403,7 +3400,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3912,6 +3921,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..491747c113 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v49 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v50 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v51 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 194 ++++-------------------
 src/backend/postmaster/postmaster.c      |  83 +++++-----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 94 insertions(+), 236 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c219780c60 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,13 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,148 +75,29 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	ProcGlobal->archiverLatch = NULL;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..fd509869aa 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving of remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d71700a565 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -350,6 +350,8 @@ typedef struct PROC_HDR
 	Latch	   *walwriterLatch;
 	/* Checkpointer process's latch */
 	Latch	   *checkpointerLatch;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 	/* Current shared estimate of appropriate spins_per_delay value */
 	int			spins_per_delay;
 	/* The proc of the Startup process, since not in ProcArray */
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v52 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 224 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  83 ++++-----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 9 files changed, 139 insertions(+), 222 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..2558bcfb08 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,13 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c399e6c267 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,68 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	*latch;		/* latch to wake the archiver up */
+	slock_t  mutex;		/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size	size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool	found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver ", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	*latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +210,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +248,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +270,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..34c8551288 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v45 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index db0cfaa360..aabf9d73eb 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 0786fcf103..430d438303 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -354,6 +354,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Jan__8_10_24_34_2021_185)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v45-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v46 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index c87ffc6549..a1e51c5b99 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 0786fcf103..430d438303 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -354,6 +354,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Thu_Jan_14_15_14_25_2021_903)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v46-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v47 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index c87ffc6549..a1e51c5b99 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 683ab64f76..6cdaf3753d 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -355,6 +355,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Thu_Jan_21_12_03_48_2021_284)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v47-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v48 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..22e1cd244c 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3403,7 +3400,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3912,6 +3921,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..491747c113 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v49 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v50 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v51 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 194 ++++-------------------
 src/backend/postmaster/postmaster.c      |  83 +++++-----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 94 insertions(+), 236 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c219780c60 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,13 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,148 +75,29 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	ProcGlobal->archiverLatch = NULL;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..fd509869aa 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving of remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d71700a565 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -350,6 +350,8 @@ typedef struct PROC_HDR
 	Latch	   *walwriterLatch;
 	/* Checkpointer process's latch */
 	Latch	   *checkpointerLatch;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 	/* Current shared estimate of appropriate spins_per_delay value */
 	int			spins_per_delay;
 	/* The proc of the Startup process, since not in ProcArray */
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v52 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 224 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  83 ++++-----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 9 files changed, 139 insertions(+), 222 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..2558bcfb08 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,13 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c399e6c267 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,68 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	*latch;		/* latch to wake the archiver up */
+	slock_t  mutex;		/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size	size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool	found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver ", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	*latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +210,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +248,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +270,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..34c8551288 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v45 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index db0cfaa360..aabf9d73eb 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 0786fcf103..430d438303 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -354,6 +354,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Jan__8_10_24_34_2021_185)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v45-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v46 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index c87ffc6549..a1e51c5b99 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 0786fcf103..430d438303 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -354,6 +354,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Thu_Jan_14_15_14_25_2021_903)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v46-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v47 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index c87ffc6549..a1e51c5b99 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 683ab64f76..6cdaf3753d 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -355,6 +355,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Thu_Jan_21_12_03_48_2021_284)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v47-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v48 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..22e1cd244c 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3403,7 +3400,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3912,6 +3921,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..491747c113 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v49 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v50 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v51 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 194 ++++-------------------
 src/backend/postmaster/postmaster.c      |  83 +++++-----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 94 insertions(+), 236 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c219780c60 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,13 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,148 +75,29 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	ProcGlobal->archiverLatch = NULL;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..fd509869aa 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving of remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d71700a565 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -350,6 +350,8 @@ typedef struct PROC_HDR
 	Latch	   *walwriterLatch;
 	/* Checkpointer process's latch */
 	Latch	   *checkpointerLatch;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 	/* Current shared estimate of appropriate spins_per_delay value */
 	int			spins_per_delay;
 	/* The proc of the Startup process, since not in ProcArray */
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v52 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 224 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  83 ++++-----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 9 files changed, 139 insertions(+), 222 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..2558bcfb08 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,13 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c399e6c267 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,68 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	*latch;		/* latch to wake the archiver up */
+	slock_t  mutex;		/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size	size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool	found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver ", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	*latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +210,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +248,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +270,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..34c8551288 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v45 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index db0cfaa360..aabf9d73eb 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 0786fcf103..430d438303 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -354,6 +354,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Jan__8_10_24_34_2021_185)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v45-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v46 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index c87ffc6549..a1e51c5b99 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 0786fcf103..430d438303 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -354,6 +354,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Thu_Jan_14_15_14_25_2021_903)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v46-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v47 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index c87ffc6549..a1e51c5b99 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 683ab64f76..6cdaf3753d 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -355,6 +355,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Thu_Jan_21_12_03_48_2021_284)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v47-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v48 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..22e1cd244c 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3403,7 +3400,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3912,6 +3921,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..491747c113 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v49 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v50 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v51 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 194 ++++-------------------
 src/backend/postmaster/postmaster.c      |  83 +++++-----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 94 insertions(+), 236 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c219780c60 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,13 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,148 +75,29 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	ProcGlobal->archiverLatch = NULL;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..fd509869aa 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving of remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d71700a565 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -350,6 +350,8 @@ typedef struct PROC_HDR
 	Latch	   *walwriterLatch;
 	/* Checkpointer process's latch */
 	Latch	   *checkpointerLatch;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 	/* Current shared estimate of appropriate spins_per_delay value */
 	int			spins_per_delay;
 	/* The proc of the Startup process, since not in ProcArray */
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v52 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 224 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  83 ++++-----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 9 files changed, 139 insertions(+), 222 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..2558bcfb08 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,13 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c399e6c267 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,68 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	*latch;		/* latch to wake the archiver up */
+	slock_t  mutex;		/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size	size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool	found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver ", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	*latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +210,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +248,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +270,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..34c8551288 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v48 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..22e1cd244c 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3403,7 +3400,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3912,6 +3921,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..491747c113 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v49 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v50 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v51 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 194 ++++-------------------
 src/backend/postmaster/postmaster.c      |  83 +++++-----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 94 insertions(+), 236 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c219780c60 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,13 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,148 +75,29 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	ProcGlobal->archiverLatch = NULL;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..fd509869aa 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving of remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d71700a565 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -350,6 +350,8 @@ typedef struct PROC_HDR
 	Latch	   *walwriterLatch;
 	/* Checkpointer process's latch */
 	Latch	   *checkpointerLatch;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 	/* Current shared estimate of appropriate spins_per_delay value */
 	int			spins_per_delay;
 	/* The proc of the Startup process, since not in ProcArray */
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v52 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 224 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  83 ++++-----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 9 files changed, 139 insertions(+), 222 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..2558bcfb08 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,13 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c399e6c267 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,68 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	*latch;		/* latch to wake the archiver up */
+	slock_t  mutex;		/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size	size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool	found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver ", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	*latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +210,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +248,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +270,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..34c8551288 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v45 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index db0cfaa360..aabf9d73eb 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 0786fcf103..430d438303 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -354,6 +354,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Jan__8_10_24_34_2021_185)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v45-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v46 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index c87ffc6549..a1e51c5b99 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 0786fcf103..430d438303 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -354,6 +354,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Thu_Jan_14_15_14_25_2021_903)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v46-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v47 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index c87ffc6549..a1e51c5b99 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 683ab64f76..6cdaf3753d 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -355,6 +355,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Thu_Jan_21_12_03_48_2021_284)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v47-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v48 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..22e1cd244c 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3403,7 +3400,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3912,6 +3921,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..491747c113 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v49 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v50 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v51 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 194 ++++-------------------
 src/backend/postmaster/postmaster.c      |  83 +++++-----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 94 insertions(+), 236 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c219780c60 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,13 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,148 +75,29 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	ProcGlobal->archiverLatch = NULL;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..fd509869aa 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving of remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d71700a565 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -350,6 +350,8 @@ typedef struct PROC_HDR
 	Latch	   *walwriterLatch;
 	/* Checkpointer process's latch */
 	Latch	   *checkpointerLatch;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 	/* Current shared estimate of appropriate spins_per_delay value */
 	int			spins_per_delay;
 	/* The proc of the Startup process, since not in ProcArray */
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v52 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 224 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  83 ++++-----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 9 files changed, 139 insertions(+), 222 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..2558bcfb08 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,13 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c399e6c267 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,68 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	*latch;		/* latch to wake the archiver up */
+	slock_t  mutex;		/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size	size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool	found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver ", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	*latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +210,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +248,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +270,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..34c8551288 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v45 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index db0cfaa360..aabf9d73eb 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 0786fcf103..430d438303 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -354,6 +354,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Jan__8_10_24_34_2021_185)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v45-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v46 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index c87ffc6549..a1e51c5b99 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 0786fcf103..430d438303 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -354,6 +354,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Thu_Jan_14_15_14_25_2021_903)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v46-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v47 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index c87ffc6549..a1e51c5b99 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 683ab64f76..6cdaf3753d 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -355,6 +355,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Thu_Jan_21_12_03_48_2021_284)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v47-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v48 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..22e1cd244c 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3403,7 +3400,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3912,6 +3921,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..491747c113 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v49 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v50 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v51 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 194 ++++-------------------
 src/backend/postmaster/postmaster.c      |  83 +++++-----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 94 insertions(+), 236 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c219780c60 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,13 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,148 +75,29 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	ProcGlobal->archiverLatch = NULL;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..fd509869aa 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving of remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d71700a565 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -350,6 +350,8 @@ typedef struct PROC_HDR
 	Latch	   *walwriterLatch;
 	/* Checkpointer process's latch */
 	Latch	   *checkpointerLatch;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 	/* Current shared estimate of appropriate spins_per_delay value */
 	int			spins_per_delay;
 	/* The proc of the Startup process, since not in ProcArray */
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v52 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 224 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  83 ++++-----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 9 files changed, 139 insertions(+), 222 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..2558bcfb08 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,13 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c399e6c267 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,68 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	*latch;		/* latch to wake the archiver up */
+	slock_t  mutex;		/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size	size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool	found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver ", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	*latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +210,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +248,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +270,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..34c8551288 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v45 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index db0cfaa360..aabf9d73eb 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 0786fcf103..430d438303 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -354,6 +354,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Jan__8_10_24_34_2021_185)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v45-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v46 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index c87ffc6549..a1e51c5b99 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 0786fcf103..430d438303 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -354,6 +354,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Thu_Jan_14_15_14_25_2021_903)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v46-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v47 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index c87ffc6549..a1e51c5b99 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 683ab64f76..6cdaf3753d 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -355,6 +355,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Thu_Jan_21_12_03_48_2021_284)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v47-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v48 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..22e1cd244c 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3403,7 +3400,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,6 +3606,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3912,6 +3921,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5140,7 +5150,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5204,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5445,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..491747c113 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Mar__5_17_18_56_2021_497)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v48-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v49 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_16_53_11_2021_575)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v49-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v50 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 174 +++--------------------
 src/backend/postmaster/postmaster.c      |  88 ++++++------
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 83 insertions(+), 232 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..e237cedaff 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,25 +79,17 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -105,121 +98,9 @@ static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +112,24 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..d9f8d82650 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3126,6 +3127,18 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  We treat it the same way to WAL receiver.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			continue;
+		}
+
 		/*
 		 * Was it the autovacuum launcher?	Normal exit can be ignored; we'll
 		 * start a new one at the next iteration of the postmaster's main
@@ -3141,24 +3154,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3403,7 +3398,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3604,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3904,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -4989,6 +4982,19 @@ SubPostmasterMain(int argc, char *argv[])
 
 		AuxiliaryProcessMain(argc - 2, argv + 2);	/* does not return */
 	}
+	if (strcmp(argv[1], "--forkarch") == 0)
+	{
+		/* Restore basic shared memory pointers */
+		InitShmemAccess(UsedShmemSegAddr);
+
+		/* Need a PGPROC to run CreateSharedMemoryAndSemaphores */
+		InitAuxiliaryProcess();
+
+		/* Attach process to shared data structures */
+		CreateSharedMemoryAndSemaphores();
+
+		PgArchiverMain(); /* does not return */
+	}
 	if (strcmp(argv[1], "--forkavlauncher") == 0)
 	{
 		/* Restore basic shared memory pointers */
@@ -5037,12 +5043,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5140,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5194,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5435,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d73890b228 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -357,6 +357,8 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Tue_Mar__9_18_29_34_2021_806)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v50-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v51 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   7 +-
 src/backend/bootstrap/bootstrap.c        |  22 +--
 src/backend/postmaster/pgarch.c          | 194 ++++-------------------
 src/backend/postmaster/postmaster.c      |  83 +++++-----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  10 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |  10 +-
 9 files changed, 94 insertions(+), 236 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..8b66a30931 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,8 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +491,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c219780c60 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,13 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,148 +75,29 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
-}
-#endif							/* EXEC_BACKEND */
-
-
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,31 +109,27 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
-	exit(0);
-}
-
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	proc_exit(0);
 }
 
 /* SIGUSR2 signal handler for archiver process */
@@ -282,14 +156,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +194,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +216,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +602,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	ProcGlobal->archiverLatch = NULL;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..fd509869aa 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving of remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index 897045ee27..bf5d6da89b 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..737ed69e57 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,6 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..d71700a565 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -350,6 +350,8 @@ typedef struct PROC_HDR
 	Latch	   *walwriterLatch;
 	/* Checkpointer process's latch */
 	Latch	   *checkpointerLatch;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
 	/* Current shared estimate of appropriate spins_per_delay value */
 	int			spins_per_delay;
 	/* The proc of the Startup process, since not in ProcArray */
@@ -370,11 +372,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_12_10_39_2021_432)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v51-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v52 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 224 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  83 ++++-----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 9 files changed, 139 insertions(+), 222 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..2558bcfb08 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,13 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
+#include "storage/latch.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +493,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..c399e6c267 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,68 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	*latch;		/* latch to wake the archiver up */
+	slock_t  mutex;		/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size	size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool	found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver ", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +144,48 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	*latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +210,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +248,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +270,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +656,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ *  exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..34c8551288 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3141,24 +3142,6 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
-		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
-		 */
-		if (pid == PgArchPID)
-		{
-			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
-			continue;
-		}
-
 		/*
 		 * Was it the statistics collector?  If so, just try to start a new
 		 * one; no need to force reset of the rest of the system.  (If fail,
@@ -3175,6 +3158,26 @@ reaper(SIGNAL_ARGS)
 			continue;
 		}
 
+		/*
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
+		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 */
+		if (pid == PgArchPID)
+		{
+			PgArchPID = 0;
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
+			if (PgArchStartupAllowed())
+				PgArchPID = StartArchiver();
+			continue;
+		}
+
 		/* Was it the system logger?  If so, try to start a new one */
 		if (pid == SysLoggerPID)
 		{
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
-- 
2.27.0


----Next_Part(Wed_Mar_10_17_51_37_2021_192)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v52-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v45 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index db0cfaa360..aabf9d73eb 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 0786fcf103..430d438303 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -354,6 +354,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Fri_Jan__8_10_24_34_2021_185)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v45-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v46 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index c87ffc6549..a1e51c5b99 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 0786fcf103..430d438303 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -354,6 +354,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Thu_Jan_14_15_14_25_2021_903)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v46-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v47 3/7] Make archiver process an auxiliary process
@ 2020-03-13 07:59  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2020-03-13 07:59 UTC (permalink / raw)

This is a preliminary patch for shared-memory based stats collector.

Archiver process must be a auxiliary process since it uses shared
memory after stats data was moved into shared-memory. Make the process
an auxiliary process in order to make it work.
---
 src/backend/access/transam/xlogarchive.c |   6 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++--
 src/backend/postmaster/pgarch.c          | 130 +++--------------------
 src/backend/postmaster/postmaster.c      |  50 +++++----
 src/backend/storage/lmgr/proc.c          |   1 +
 src/include/access/xlog.h                |   3 +
 src/include/access/xlogarchive.h         |   1 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |   4 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   3 +
 11 files changed, 69 insertions(+), 154 deletions(-)

diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..d01859bde5 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -29,7 +29,9 @@
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
+#include "storage/latch.h"
 #include "storage/pmsignal.h"
+#include "storage/proc.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -490,8 +492,8 @@ XLogArchiveNotify(const char *xlog)
 	}
 
 	/* Notify archiver that it's got something to do */
-	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+	if (IsUnderPostmaster && ProcGlobal->archiverLatch)
+		SetLatch(ProcGlobal->archiverLatch);
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..9a2e21bf86 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -48,6 +48,7 @@
 #include "storage/latch.h"
 #include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -78,13 +79,11 @@
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
@@ -95,8 +94,6 @@ static volatile sig_atomic_t ready_to_stop = false;
 static pid_t pgarch_forkexec(void);
 #endif
 
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
@@ -110,75 +107,6 @@ static void pgarch_archiveDone(char *xlog);
  * ------------------------------------------------------------
  */
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
-
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
 /* ------------------------------------------------------------
  * Local functions called by archiver follow
  * ------------------------------------------------------------
@@ -212,14 +140,9 @@ pgarch_forkexec(void)
 #endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +154,26 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	ProcGlobal->archiverLatch = &MyProc->procLatch;
 
 	pgarch_MainLoop();
 
 	exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
-{
-	int			save_errno = errno;
-
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
-}
-
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +198,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +236,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +258,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 7de27ee4e0..af91c313e2 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1788,7 +1789,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3027,7 +3028,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3162,20 +3163,16 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
-		 * PostmasterStateMachine() will advance to the next shutdown step.
+		 * Was it the archiver?  Normal exit can be ignored; we'll start a new
+		 * one at the next iteration of the postmaster's main loop, if
+		 * necessary. Any other exit condition is treated as a crash.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
 			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
-			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			continue;
 		}
 
@@ -3423,7 +3420,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3629,6 +3626,18 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
+	{
+		ereport(DEBUG2,
+				(errmsg_internal("sending %s to process %d",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
+								 (int) PgArchPID)));
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
+	}
+
 	/*
 	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
 	 * necessary, but it seems like a good idea for robustness, and it
@@ -3932,6 +3941,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5160,7 +5170,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5214,16 +5224,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5465,6 +5465,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c
index c87ffc6549..a1e51c5b99 100644
--- a/src/backend/storage/lmgr/proc.c
+++ b/src/backend/storage/lmgr/proc.c
@@ -182,6 +182,7 @@ InitProcGlobal(void)
 	ProcGlobal->startupBufferPinWaitBufId = -1;
 	ProcGlobal->walwriterLatch = NULL;
 	ProcGlobal->checkpointerLatch = NULL;
+	ProcGlobal->archiverLatch = NULL;
 	pg_atomic_init_u32(&ProcGlobal->procArrayGroupFirst, INVALID_PGPROCNO);
 	pg_atomic_init_u32(&ProcGlobal->clogGroupFirst, INVALID_PGPROCNO);
 
diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h
index 75ec1073bd..551f518cc2 100644
--- a/src/include/access/xlog.h
+++ b/src/include/access/xlog.h
@@ -339,6 +339,9 @@ extern XLogRecPtr GetRedoRecPtr(void);
 extern XLogRecPtr GetInsertRecPtr(void);
 extern XLogRecPtr GetFlushRecPtr(void);
 extern XLogRecPtr GetLastImportantRecPtr(void);
+extern void XLogArchiveWakeupStart(void);
+extern void XLogArchiveWakeupEnd(void);
+extern void XLogArchiveWakeup(void);
 extern void RemovePromoteSignalFiles(void);
 
 extern bool PromoteIsTriggered(void);
diff --git a/src/include/access/xlogarchive.h b/src/include/access/xlogarchive.h
index 3edd1a976c..1a59181cf9 100644
--- a/src/include/access/xlogarchive.h
+++ b/src/include/access/xlogarchive.h
@@ -25,6 +25,7 @@ extern void ExecuteRecoveryCommand(const char *command, const char *commandName,
 extern void KeepFileRestoredFromArchive(const char *path, const char *xlogfname);
 extern void XLogArchiveNotify(const char *xlog);
 extern void XLogArchiveNotifySeg(XLogSegNo segno);
+extern void XLogArchiveWakeup(void);
 extern void XLogArchiveForceDone(const char *xlog);
 extern bool XLogArchiveCheckDone(const char *xlog);
 extern bool XLogArchiveIsBusy(const char *xlog);
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 1bdc97e308..adb9f819bb 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -419,6 +419,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -431,6 +432,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..385b002dfe 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -32,8 +32,6 @@
  */
 extern int	pgarch_start(void);
 
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern void PgArchiverMain(void) pg_attribute_noreturn();
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index 683ab64f76..6cdaf3753d 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -355,6 +355,9 @@ typedef struct PROC_HDR
 	int			startupProcPid;
 	/* Buffer id of the buffer that Startup process waits for pin on, or -1 */
 	int			startupBufferPinWaitBufId;
+	/* Archiver process's latch */
+	Latch	   *archiverLatch;
+	/* Current shared estimate of appropriate spins_per_delay value */
 } PROC_HDR;
 
 extern PGDLLIMPORT PROC_HDR *ProcGlobal;
-- 
2.27.0


----Next_Part(Thu_Jan_21_12_03_48_2021_284)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v47-0004-Shared-memory-based-stats-collector.patch"



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v55 3/3] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 240 ++++++++++-------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 164 insertions(+), 212 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..07ba989a37 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,101 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int			pgprocno;		/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
-
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	Size		size = 0;
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	size = add_size(size, sizeof(PgArchData));
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
+	return size;
+}
 
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-			PgArchiverMain(0, NULL);
-			break;
-#endif
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-		default:
-			return (int) pgArchPid;
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
 	}
-
-	/* shouldn't get here */
-	return 0;
 }
 
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
 /*
- * pgarch_forkexec() -
+ *  PgArchIsSuppressed
  *
- * Format up the arglist for, then fork and exec, archive process
+ * Return true if archiver relaunch is suppressed.
+ *
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-static pid_t
-pgarch_forkexec(void)
+bool
+PgArchCanRestart(void)
 {
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
+	static time_t last_pgarch_start_time = 0;
+	time_t		curtime = time(NULL);
 
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
+	/*
+	 * allow to launch also for the first time and when something's wrong in
+	 * the time values.
+	 */
+	if (last_pgarch_start_time == 0 ||
+		curtime < last_pgarch_start_time ||
+		(curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL)
+	{
+		last_pgarch_start_time = curtime;
 
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
+		return true;
+	}
 
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our pgproc index so that backends can use our latch to wake
+	 * us up while we're sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int			arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will
+	 * be relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +246,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +284,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +306,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..e8af05c04e 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||			\
+	  (XLogArchivingAlways() &&									  \
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 PgArchCanRestart())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for
+		 * it to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and
+		 * syslogger processes are disregarded since they are not connected to
+		 * shared memory; we also disregard dead_end children here. Walsenders
+		 * and archiver are also disregarded, they will be terminated later
+		 * after writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..1e47a143e1 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchCanRestart(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_17_24_43_2021_866)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v54 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 241 +++++++++--------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 160 insertions(+), 217 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..8e572afea3 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,6 +71,12 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int		pgprocno;				/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
@@ -80,146 +84,79 @@
  */
 static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
+
+	return size;
+}
+
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
+
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
+
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
+	}
+}
 
 /*
- * pgarch_start
+ *  PgArchIsSuppressed
  *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
+ * Return true if archiver relaunch is suppressed.
  *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-int
-pgarch_start(void)
+bool
+PgArchIsSuppressed(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	time_t	curtime = time(NULL);
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+	if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL)
+		return true;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
 	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int	arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will be
+	 * relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +237,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +275,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +297,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..4f8e364284 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||	\
+	  (XLogArchivingAlways() &&									\
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 !PgArchIsSuppressed())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..640692d33e 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchIsSuppressed(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_13_49_06_2021_682)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v55 3/3] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 240 ++++++++++-------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 164 insertions(+), 212 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..07ba989a37 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,101 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int			pgprocno;		/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
-
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	Size		size = 0;
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	size = add_size(size, sizeof(PgArchData));
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
+	return size;
+}
 
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-			PgArchiverMain(0, NULL);
-			break;
-#endif
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-		default:
-			return (int) pgArchPid;
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
 	}
-
-	/* shouldn't get here */
-	return 0;
 }
 
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
 /*
- * pgarch_forkexec() -
+ *  PgArchIsSuppressed
  *
- * Format up the arglist for, then fork and exec, archive process
+ * Return true if archiver relaunch is suppressed.
+ *
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-static pid_t
-pgarch_forkexec(void)
+bool
+PgArchCanRestart(void)
 {
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
+	static time_t last_pgarch_start_time = 0;
+	time_t		curtime = time(NULL);
 
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
+	/*
+	 * allow to launch also for the first time and when something's wrong in
+	 * the time values.
+	 */
+	if (last_pgarch_start_time == 0 ||
+		curtime < last_pgarch_start_time ||
+		(curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL)
+	{
+		last_pgarch_start_time = curtime;
 
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
+		return true;
+	}
 
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our pgproc index so that backends can use our latch to wake
+	 * us up while we're sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int			arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will
+	 * be relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +246,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +284,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +306,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..e8af05c04e 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||			\
+	  (XLogArchivingAlways() &&									  \
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 PgArchCanRestart())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for
+		 * it to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and
+		 * syslogger processes are disregarded since they are not connected to
+		 * shared memory; we also disregard dead_end children here. Walsenders
+		 * and archiver are also disregarded, they will be terminated later
+		 * after writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..1e47a143e1 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchCanRestart(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_17_24_43_2021_866)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v53 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 227 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  74 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 137 insertions(+), 218 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..818c9a1f3f 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,70 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	   *latch;			/* latch to wake the archiver up */
+	slock_t		mutex;			/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	   *latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	/* fetching the latch pointer might not be atomic, so use spinlock */
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +213,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +251,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +273,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..460e629145 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3804,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3911,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_09_23_13_2021_947)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v54 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 241 +++++++++--------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 160 insertions(+), 217 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..8e572afea3 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,6 +71,12 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int		pgprocno;				/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
@@ -80,146 +84,79 @@
  */
 static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
+
+	return size;
+}
+
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
+
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
+
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
+	}
+}
 
 /*
- * pgarch_start
+ *  PgArchIsSuppressed
  *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
+ * Return true if archiver relaunch is suppressed.
  *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-int
-pgarch_start(void)
+bool
+PgArchIsSuppressed(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	time_t	curtime = time(NULL);
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+	if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL)
+		return true;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
 	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int	arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will be
+	 * relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +237,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +275,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +297,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..4f8e364284 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||	\
+	  (XLogArchivingAlways() &&									\
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 !PgArchIsSuppressed())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..640692d33e 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchIsSuppressed(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_13_49_06_2021_682)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v55 3/3] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 240 ++++++++++-------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 164 insertions(+), 212 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..07ba989a37 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,101 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int			pgprocno;		/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
-
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	Size		size = 0;
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	size = add_size(size, sizeof(PgArchData));
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
+	return size;
+}
 
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-			PgArchiverMain(0, NULL);
-			break;
-#endif
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-		default:
-			return (int) pgArchPid;
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
 	}
-
-	/* shouldn't get here */
-	return 0;
 }
 
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
 /*
- * pgarch_forkexec() -
+ *  PgArchIsSuppressed
  *
- * Format up the arglist for, then fork and exec, archive process
+ * Return true if archiver relaunch is suppressed.
+ *
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-static pid_t
-pgarch_forkexec(void)
+bool
+PgArchCanRestart(void)
 {
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
+	static time_t last_pgarch_start_time = 0;
+	time_t		curtime = time(NULL);
 
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
+	/*
+	 * allow to launch also for the first time and when something's wrong in
+	 * the time values.
+	 */
+	if (last_pgarch_start_time == 0 ||
+		curtime < last_pgarch_start_time ||
+		(curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL)
+	{
+		last_pgarch_start_time = curtime;
 
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
+		return true;
+	}
 
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our pgproc index so that backends can use our latch to wake
+	 * us up while we're sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int			arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will
+	 * be relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +246,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +284,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +306,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..e8af05c04e 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||			\
+	  (XLogArchivingAlways() &&									  \
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 PgArchCanRestart())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for
+		 * it to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and
+		 * syslogger processes are disregarded since they are not connected to
+		 * shared memory; we also disregard dead_end children here. Walsenders
+		 * and archiver are also disregarded, they will be terminated later
+		 * after writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..1e47a143e1 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchCanRestart(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_17_24_43_2021_866)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v53 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 227 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  74 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 137 insertions(+), 218 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..818c9a1f3f 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,70 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	   *latch;			/* latch to wake the archiver up */
+	slock_t		mutex;			/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	   *latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	/* fetching the latch pointer might not be atomic, so use spinlock */
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +213,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +251,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +273,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..460e629145 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3804,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3911,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_09_23_13_2021_947)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v54 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 241 +++++++++--------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 160 insertions(+), 217 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..8e572afea3 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,6 +71,12 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int		pgprocno;				/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
@@ -80,146 +84,79 @@
  */
 static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
+
+	return size;
+}
+
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
+
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
+
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
+	}
+}
 
 /*
- * pgarch_start
+ *  PgArchIsSuppressed
  *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
+ * Return true if archiver relaunch is suppressed.
  *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-int
-pgarch_start(void)
+bool
+PgArchIsSuppressed(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	time_t	curtime = time(NULL);
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+	if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL)
+		return true;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
 	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int	arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will be
+	 * relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +237,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +275,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +297,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..4f8e364284 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||	\
+	  (XLogArchivingAlways() &&									\
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 !PgArchIsSuppressed())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..640692d33e 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchIsSuppressed(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_13_49_06_2021_682)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v55 3/3] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 240 ++++++++++-------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 164 insertions(+), 212 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..07ba989a37 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,101 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int			pgprocno;		/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
-
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	Size		size = 0;
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	size = add_size(size, sizeof(PgArchData));
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
+	return size;
+}
 
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-			PgArchiverMain(0, NULL);
-			break;
-#endif
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-		default:
-			return (int) pgArchPid;
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
 	}
-
-	/* shouldn't get here */
-	return 0;
 }
 
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
 /*
- * pgarch_forkexec() -
+ *  PgArchIsSuppressed
  *
- * Format up the arglist for, then fork and exec, archive process
+ * Return true if archiver relaunch is suppressed.
+ *
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-static pid_t
-pgarch_forkexec(void)
+bool
+PgArchCanRestart(void)
 {
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
+	static time_t last_pgarch_start_time = 0;
+	time_t		curtime = time(NULL);
 
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
+	/*
+	 * allow to launch also for the first time and when something's wrong in
+	 * the time values.
+	 */
+	if (last_pgarch_start_time == 0 ||
+		curtime < last_pgarch_start_time ||
+		(curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL)
+	{
+		last_pgarch_start_time = curtime;
 
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
+		return true;
+	}
 
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our pgproc index so that backends can use our latch to wake
+	 * us up while we're sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int			arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will
+	 * be relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +246,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +284,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +306,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..e8af05c04e 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||			\
+	  (XLogArchivingAlways() &&									  \
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 PgArchCanRestart())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for
+		 * it to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and
+		 * syslogger processes are disregarded since they are not connected to
+		 * shared memory; we also disregard dead_end children here. Walsenders
+		 * and archiver are also disregarded, they will be terminated later
+		 * after writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..1e47a143e1 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchCanRestart(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_17_24_43_2021_866)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v53 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 227 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  74 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 137 insertions(+), 218 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..818c9a1f3f 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,70 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	   *latch;			/* latch to wake the archiver up */
+	slock_t		mutex;			/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	   *latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	/* fetching the latch pointer might not be atomic, so use spinlock */
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +213,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +251,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +273,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..460e629145 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3804,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3911,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_09_23_13_2021_947)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v54 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 241 +++++++++--------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 160 insertions(+), 217 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..8e572afea3 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,6 +71,12 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int		pgprocno;				/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
@@ -80,146 +84,79 @@
  */
 static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
+
+	return size;
+}
+
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
+
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
+
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
+	}
+}
 
 /*
- * pgarch_start
+ *  PgArchIsSuppressed
  *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
+ * Return true if archiver relaunch is suppressed.
  *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-int
-pgarch_start(void)
+bool
+PgArchIsSuppressed(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	time_t	curtime = time(NULL);
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+	if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL)
+		return true;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
 	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int	arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will be
+	 * relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +237,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +275,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +297,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..4f8e364284 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||	\
+	  (XLogArchivingAlways() &&									\
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 !PgArchIsSuppressed())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..640692d33e 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchIsSuppressed(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_13_49_06_2021_682)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v55 3/3] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 240 ++++++++++-------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 164 insertions(+), 212 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..07ba989a37 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,101 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int			pgprocno;		/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
-
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	Size		size = 0;
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	size = add_size(size, sizeof(PgArchData));
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
+	return size;
+}
 
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-			PgArchiverMain(0, NULL);
-			break;
-#endif
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-		default:
-			return (int) pgArchPid;
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
 	}
-
-	/* shouldn't get here */
-	return 0;
 }
 
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
 /*
- * pgarch_forkexec() -
+ *  PgArchIsSuppressed
  *
- * Format up the arglist for, then fork and exec, archive process
+ * Return true if archiver relaunch is suppressed.
+ *
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-static pid_t
-pgarch_forkexec(void)
+bool
+PgArchCanRestart(void)
 {
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
+	static time_t last_pgarch_start_time = 0;
+	time_t		curtime = time(NULL);
 
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
+	/*
+	 * allow to launch also for the first time and when something's wrong in
+	 * the time values.
+	 */
+	if (last_pgarch_start_time == 0 ||
+		curtime < last_pgarch_start_time ||
+		(curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL)
+	{
+		last_pgarch_start_time = curtime;
 
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
+		return true;
+	}
 
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our pgproc index so that backends can use our latch to wake
+	 * us up while we're sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int			arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will
+	 * be relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +246,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +284,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +306,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..e8af05c04e 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||			\
+	  (XLogArchivingAlways() &&									  \
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 PgArchCanRestart())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for
+		 * it to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and
+		 * syslogger processes are disregarded since they are not connected to
+		 * shared memory; we also disregard dead_end children here. Walsenders
+		 * and archiver are also disregarded, they will be terminated later
+		 * after writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..1e47a143e1 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchCanRestart(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_17_24_43_2021_866)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v53 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 227 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  74 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 137 insertions(+), 218 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..818c9a1f3f 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,70 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	   *latch;			/* latch to wake the archiver up */
+	slock_t		mutex;			/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	   *latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	/* fetching the latch pointer might not be atomic, so use spinlock */
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +213,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +251,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +273,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..460e629145 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3804,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3911,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_09_23_13_2021_947)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v54 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 241 +++++++++--------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 160 insertions(+), 217 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..8e572afea3 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,6 +71,12 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int		pgprocno;				/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
@@ -80,146 +84,79 @@
  */
 static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
+
+	return size;
+}
+
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
+
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
+
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
+	}
+}
 
 /*
- * pgarch_start
+ *  PgArchIsSuppressed
  *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
+ * Return true if archiver relaunch is suppressed.
  *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-int
-pgarch_start(void)
+bool
+PgArchIsSuppressed(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	time_t	curtime = time(NULL);
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+	if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL)
+		return true;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
 	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int	arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will be
+	 * relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +237,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +275,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +297,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..4f8e364284 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||	\
+	  (XLogArchivingAlways() &&									\
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 !PgArchIsSuppressed())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..640692d33e 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchIsSuppressed(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_13_49_06_2021_682)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v55 3/3] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 240 ++++++++++-------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 164 insertions(+), 212 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..07ba989a37 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,101 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int			pgprocno;		/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
-
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	Size		size = 0;
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	size = add_size(size, sizeof(PgArchData));
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
+	return size;
+}
 
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-			PgArchiverMain(0, NULL);
-			break;
-#endif
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-		default:
-			return (int) pgArchPid;
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
 	}
-
-	/* shouldn't get here */
-	return 0;
 }
 
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
 /*
- * pgarch_forkexec() -
+ *  PgArchIsSuppressed
  *
- * Format up the arglist for, then fork and exec, archive process
+ * Return true if archiver relaunch is suppressed.
+ *
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-static pid_t
-pgarch_forkexec(void)
+bool
+PgArchCanRestart(void)
 {
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
+	static time_t last_pgarch_start_time = 0;
+	time_t		curtime = time(NULL);
 
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
+	/*
+	 * allow to launch also for the first time and when something's wrong in
+	 * the time values.
+	 */
+	if (last_pgarch_start_time == 0 ||
+		curtime < last_pgarch_start_time ||
+		(curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL)
+	{
+		last_pgarch_start_time = curtime;
 
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
+		return true;
+	}
 
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our pgproc index so that backends can use our latch to wake
+	 * us up while we're sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int			arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will
+	 * be relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +246,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +284,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +306,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..e8af05c04e 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||			\
+	  (XLogArchivingAlways() &&									  \
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 PgArchCanRestart())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for
+		 * it to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and
+		 * syslogger processes are disregarded since they are not connected to
+		 * shared memory; we also disregard dead_end children here. Walsenders
+		 * and archiver are also disregarded, they will be terminated later
+		 * after writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..1e47a143e1 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchCanRestart(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_17_24_43_2021_866)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v53 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 227 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  74 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 137 insertions(+), 218 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..818c9a1f3f 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,70 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	   *latch;			/* latch to wake the archiver up */
+	slock_t		mutex;			/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	   *latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	/* fetching the latch pointer might not be atomic, so use spinlock */
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +213,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +251,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +273,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..460e629145 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3804,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3911,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_09_23_13_2021_947)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v53 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 227 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  74 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 137 insertions(+), 218 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..818c9a1f3f 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,70 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	   *latch;			/* latch to wake the archiver up */
+	slock_t		mutex;			/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	   *latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	/* fetching the latch pointer might not be atomic, so use spinlock */
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +213,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +251,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +273,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..460e629145 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3804,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3911,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_09_23_13_2021_947)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v54 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 241 +++++++++--------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 160 insertions(+), 217 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..8e572afea3 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,6 +71,12 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int		pgprocno;				/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
@@ -80,146 +84,79 @@
  */
 static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
+
+	return size;
+}
+
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
+
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
+
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
+	}
+}
 
 /*
- * pgarch_start
+ *  PgArchIsSuppressed
  *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
+ * Return true if archiver relaunch is suppressed.
  *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-int
-pgarch_start(void)
+bool
+PgArchIsSuppressed(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	time_t	curtime = time(NULL);
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+	if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL)
+		return true;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
 	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int	arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will be
+	 * relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +237,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +275,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +297,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..4f8e364284 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||	\
+	  (XLogArchivingAlways() &&									\
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 !PgArchIsSuppressed())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..640692d33e 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchIsSuppressed(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_13_49_06_2021_682)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v55 3/3] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 240 ++++++++++-------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 164 insertions(+), 212 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..07ba989a37 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,101 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int			pgprocno;		/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
-
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	Size		size = 0;
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	size = add_size(size, sizeof(PgArchData));
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
+	return size;
+}
 
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-			PgArchiverMain(0, NULL);
-			break;
-#endif
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-		default:
-			return (int) pgArchPid;
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
 	}
-
-	/* shouldn't get here */
-	return 0;
 }
 
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
 /*
- * pgarch_forkexec() -
+ *  PgArchIsSuppressed
  *
- * Format up the arglist for, then fork and exec, archive process
+ * Return true if archiver relaunch is suppressed.
+ *
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-static pid_t
-pgarch_forkexec(void)
+bool
+PgArchCanRestart(void)
 {
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
+	static time_t last_pgarch_start_time = 0;
+	time_t		curtime = time(NULL);
 
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
+	/*
+	 * allow to launch also for the first time and when something's wrong in
+	 * the time values.
+	 */
+	if (last_pgarch_start_time == 0 ||
+		curtime < last_pgarch_start_time ||
+		(curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL)
+	{
+		last_pgarch_start_time = curtime;
 
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
+		return true;
+	}
 
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our pgproc index so that backends can use our latch to wake
+	 * us up while we're sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int			arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will
+	 * be relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +246,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +284,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +306,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..e8af05c04e 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||			\
+	  (XLogArchivingAlways() &&									  \
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 PgArchCanRestart())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for
+		 * it to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and
+		 * syslogger processes are disregarded since they are not connected to
+		 * shared memory; we also disregard dead_end children here. Walsenders
+		 * and archiver are also disregarded, they will be terminated later
+		 * after writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..1e47a143e1 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchCanRestart(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_17_24_43_2021_866)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v53 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 227 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  74 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 137 insertions(+), 218 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..818c9a1f3f 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,70 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	   *latch;			/* latch to wake the archiver up */
+	slock_t		mutex;			/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	   *latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	/* fetching the latch pointer might not be atomic, so use spinlock */
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +213,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +251,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +273,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..460e629145 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3804,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3911,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_09_23_13_2021_947)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v54 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 241 +++++++++--------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 160 insertions(+), 217 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..8e572afea3 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,6 +71,12 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int		pgprocno;				/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
@@ -80,146 +84,79 @@
  */
 static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
+
+	return size;
+}
+
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
+
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
+
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
+	}
+}
 
 /*
- * pgarch_start
+ *  PgArchIsSuppressed
  *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
+ * Return true if archiver relaunch is suppressed.
  *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-int
-pgarch_start(void)
+bool
+PgArchIsSuppressed(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	time_t	curtime = time(NULL);
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+	if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL)
+		return true;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
 	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int	arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will be
+	 * relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +237,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +275,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +297,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..4f8e364284 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||	\
+	  (XLogArchivingAlways() &&									\
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 !PgArchIsSuppressed())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..640692d33e 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchIsSuppressed(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_13_49_06_2021_682)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v55 3/3] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 240 ++++++++++-------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 164 insertions(+), 212 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..07ba989a37 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,101 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int			pgprocno;		/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
-
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	Size		size = 0;
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	size = add_size(size, sizeof(PgArchData));
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
+	return size;
+}
 
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-			PgArchiverMain(0, NULL);
-			break;
-#endif
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-		default:
-			return (int) pgArchPid;
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
 	}
-
-	/* shouldn't get here */
-	return 0;
 }
 
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
 /*
- * pgarch_forkexec() -
+ *  PgArchIsSuppressed
  *
- * Format up the arglist for, then fork and exec, archive process
+ * Return true if archiver relaunch is suppressed.
+ *
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-static pid_t
-pgarch_forkexec(void)
+bool
+PgArchCanRestart(void)
 {
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
+	static time_t last_pgarch_start_time = 0;
+	time_t		curtime = time(NULL);
 
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
+	/*
+	 * allow to launch also for the first time and when something's wrong in
+	 * the time values.
+	 */
+	if (last_pgarch_start_time == 0 ||
+		curtime < last_pgarch_start_time ||
+		(curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL)
+	{
+		last_pgarch_start_time = curtime;
 
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
+		return true;
+	}
 
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our pgproc index so that backends can use our latch to wake
+	 * us up while we're sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int			arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will
+	 * be relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +246,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +284,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +306,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..e8af05c04e 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||			\
+	  (XLogArchivingAlways() &&									  \
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 PgArchCanRestart())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for
+		 * it to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and
+		 * syslogger processes are disregarded since they are not connected to
+		 * shared memory; we also disregard dead_end children here. Walsenders
+		 * and archiver are also disregarded, they will be terminated later
+		 * after writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..1e47a143e1 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchCanRestart(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_17_24_43_2021_866)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v53 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 227 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  74 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 137 insertions(+), 218 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..818c9a1f3f 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,70 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	   *latch;			/* latch to wake the archiver up */
+	slock_t		mutex;			/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	   *latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	/* fetching the latch pointer might not be atomic, so use spinlock */
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +213,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +251,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +273,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..460e629145 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3804,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3911,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_09_23_13_2021_947)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v54 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 241 +++++++++--------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 160 insertions(+), 217 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..8e572afea3 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,6 +71,12 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int		pgprocno;				/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
@@ -80,146 +84,79 @@
  */
 static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
+
+	return size;
+}
+
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
+
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
+
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
+	}
+}
 
 /*
- * pgarch_start
+ *  PgArchIsSuppressed
  *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
+ * Return true if archiver relaunch is suppressed.
  *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-int
-pgarch_start(void)
+bool
+PgArchIsSuppressed(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	time_t	curtime = time(NULL);
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+	if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL)
+		return true;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
 	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int	arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will be
+	 * relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +237,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +275,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +297,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..4f8e364284 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||	\
+	  (XLogArchivingAlways() &&									\
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 !PgArchIsSuppressed())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..640692d33e 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchIsSuppressed(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_13_49_06_2021_682)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v53 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 227 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  74 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 137 insertions(+), 218 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..818c9a1f3f 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,70 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	   *latch;			/* latch to wake the archiver up */
+	slock_t		mutex;			/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	   *latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	/* fetching the latch pointer might not be atomic, so use spinlock */
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +213,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +251,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +273,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..460e629145 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3804,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3911,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_09_23_13_2021_947)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v54 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 241 +++++++++--------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 160 insertions(+), 217 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..8e572afea3 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,6 +71,12 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int		pgprocno;				/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
@@ -80,146 +84,79 @@
  */
 static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
+
+	return size;
+}
+
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
+
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
+
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
+	}
+}
 
 /*
- * pgarch_start
+ *  PgArchIsSuppressed
  *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
+ * Return true if archiver relaunch is suppressed.
  *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-int
-pgarch_start(void)
+bool
+PgArchIsSuppressed(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	time_t	curtime = time(NULL);
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+	if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL)
+		return true;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
 	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int	arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will be
+	 * relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +237,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +275,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +297,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..4f8e364284 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||	\
+	  (XLogArchivingAlways() &&									\
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 !PgArchIsSuppressed())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..640692d33e 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchIsSuppressed(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_13_49_06_2021_682)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v55 3/3] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 240 ++++++++++-------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 164 insertions(+), 212 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..07ba989a37 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,101 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int			pgprocno;		/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
-
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	Size		size = 0;
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	size = add_size(size, sizeof(PgArchData));
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
+	return size;
+}
 
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-			PgArchiverMain(0, NULL);
-			break;
-#endif
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-		default:
-			return (int) pgArchPid;
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
 	}
-
-	/* shouldn't get here */
-	return 0;
 }
 
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
 /*
- * pgarch_forkexec() -
+ *  PgArchIsSuppressed
  *
- * Format up the arglist for, then fork and exec, archive process
+ * Return true if archiver relaunch is suppressed.
+ *
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-static pid_t
-pgarch_forkexec(void)
+bool
+PgArchCanRestart(void)
 {
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
+	static time_t last_pgarch_start_time = 0;
+	time_t		curtime = time(NULL);
 
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
+	/*
+	 * allow to launch also for the first time and when something's wrong in
+	 * the time values.
+	 */
+	if (last_pgarch_start_time == 0 ||
+		curtime < last_pgarch_start_time ||
+		(curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL)
+	{
+		last_pgarch_start_time = curtime;
 
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
+		return true;
+	}
 
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our pgproc index so that backends can use our latch to wake
+	 * us up while we're sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int			arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will
+	 * be relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +246,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +284,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +306,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..e8af05c04e 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||			\
+	  (XLogArchivingAlways() &&									  \
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 PgArchCanRestart())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for
+		 * it to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and
+		 * syslogger processes are disregarded since they are not connected to
+		 * shared memory; we also disregard dead_end children here. Walsenders
+		 * and archiver are also disregarded, they will be terminated later
+		 * after writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..1e47a143e1 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchCanRestart(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_17_24_43_2021_866)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v55 3/3] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 240 ++++++++++-------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 164 insertions(+), 212 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..07ba989a37 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,101 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int			pgprocno;		/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
-
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	Size		size = 0;
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	size = add_size(size, sizeof(PgArchData));
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
+	return size;
+}
 
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-			PgArchiverMain(0, NULL);
-			break;
-#endif
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-		default:
-			return (int) pgArchPid;
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
 	}
-
-	/* shouldn't get here */
-	return 0;
 }
 
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
 /*
- * pgarch_forkexec() -
+ *  PgArchIsSuppressed
  *
- * Format up the arglist for, then fork and exec, archive process
+ * Return true if archiver relaunch is suppressed.
+ *
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-static pid_t
-pgarch_forkexec(void)
+bool
+PgArchCanRestart(void)
 {
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
+	static time_t last_pgarch_start_time = 0;
+	time_t		curtime = time(NULL);
 
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
+	/*
+	 * allow to launch also for the first time and when something's wrong in
+	 * the time values.
+	 */
+	if (last_pgarch_start_time == 0 ||
+		curtime < last_pgarch_start_time ||
+		(curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL)
+	{
+		last_pgarch_start_time = curtime;
 
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
+		return true;
+	}
 
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our pgproc index so that backends can use our latch to wake
+	 * us up while we're sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int			arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will
+	 * be relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +246,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +284,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +306,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..e8af05c04e 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||			\
+	  (XLogArchivingAlways() &&									  \
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 PgArchCanRestart())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for
+		 * it to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and
+		 * syslogger processes are disregarded since they are not connected to
+		 * shared memory; we also disregard dead_end children here. Walsenders
+		 * and archiver are also disregarded, they will be terminated later
+		 * after writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..1e47a143e1 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchCanRestart(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_17_24_43_2021_866)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v53 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 227 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  74 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 137 insertions(+), 218 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..818c9a1f3f 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,70 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	   *latch;			/* latch to wake the archiver up */
+	slock_t		mutex;			/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	   *latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	/* fetching the latch pointer might not be atomic, so use spinlock */
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +213,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +251,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +273,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..460e629145 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3804,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3911,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_09_23_13_2021_947)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v54 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 241 +++++++++--------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 160 insertions(+), 217 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..8e572afea3 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,6 +71,12 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int		pgprocno;				/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
@@ -80,146 +84,79 @@
  */
 static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
+
+	return size;
+}
+
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
+
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
+
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
+	}
+}
 
 /*
- * pgarch_start
+ *  PgArchIsSuppressed
  *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
+ * Return true if archiver relaunch is suppressed.
  *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-int
-pgarch_start(void)
+bool
+PgArchIsSuppressed(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	time_t	curtime = time(NULL);
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+	if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL)
+		return true;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
 	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int	arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will be
+	 * relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +237,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +275,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +297,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..4f8e364284 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||	\
+	  (XLogArchivingAlways() &&									\
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 !PgArchIsSuppressed())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..640692d33e 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchIsSuppressed(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_13_49_06_2021_682)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v53 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 227 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  74 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 137 insertions(+), 218 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..818c9a1f3f 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,70 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	   *latch;			/* latch to wake the archiver up */
+	slock_t		mutex;			/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	   *latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	/* fetching the latch pointer might not be atomic, so use spinlock */
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +213,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +251,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +273,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..460e629145 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3804,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3911,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_09_23_13_2021_947)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v54 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 241 +++++++++--------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 160 insertions(+), 217 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..8e572afea3 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,6 +71,12 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int		pgprocno;				/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
@@ -80,146 +84,79 @@
  */
 static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
+
+	return size;
+}
+
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
+
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
+
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
+	}
+}
 
 /*
- * pgarch_start
+ *  PgArchIsSuppressed
  *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
+ * Return true if archiver relaunch is suppressed.
  *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-int
-pgarch_start(void)
+bool
+PgArchIsSuppressed(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	time_t	curtime = time(NULL);
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+	if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL)
+		return true;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
 	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int	arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will be
+	 * relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +237,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +275,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +297,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..4f8e364284 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||	\
+	  (XLogArchivingAlways() &&									\
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 !PgArchIsSuppressed())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..640692d33e 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchIsSuppressed(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_13_49_06_2021_682)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v55 3/3] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 240 ++++++++++-------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 164 insertions(+), 212 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..07ba989a37 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,101 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int			pgprocno;		/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
-
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	Size		size = 0;
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	size = add_size(size, sizeof(PgArchData));
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
+	return size;
+}
 
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-			PgArchiverMain(0, NULL);
-			break;
-#endif
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-		default:
-			return (int) pgArchPid;
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
 	}
-
-	/* shouldn't get here */
-	return 0;
 }
 
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
 /*
- * pgarch_forkexec() -
+ *  PgArchIsSuppressed
  *
- * Format up the arglist for, then fork and exec, archive process
+ * Return true if archiver relaunch is suppressed.
+ *
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-static pid_t
-pgarch_forkexec(void)
+bool
+PgArchCanRestart(void)
 {
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
+	static time_t last_pgarch_start_time = 0;
+	time_t		curtime = time(NULL);
 
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
+	/*
+	 * allow to launch also for the first time and when something's wrong in
+	 * the time values.
+	 */
+	if (last_pgarch_start_time == 0 ||
+		curtime < last_pgarch_start_time ||
+		(curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL)
+	{
+		last_pgarch_start_time = curtime;
 
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
+		return true;
+	}
 
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our pgproc index so that backends can use our latch to wake
+	 * us up while we're sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int			arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will
+	 * be relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +246,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +284,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +306,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..e8af05c04e 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||			\
+	  (XLogArchivingAlways() &&									  \
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 PgArchCanRestart())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for
+		 * it to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and
+		 * syslogger processes are disregarded since they are not connected to
+		 * shared memory; we also disregard dead_end children here. Walsenders
+		 * and archiver are also disregarded, they will be terminated later
+		 * after writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..1e47a143e1 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchCanRestart(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_17_24_43_2021_866)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v55 3/3] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 240 ++++++++++-------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 164 insertions(+), 212 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..07ba989a37 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,101 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int			pgprocno;		/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
-
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	Size		size = 0;
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	size = add_size(size, sizeof(PgArchData));
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
+	return size;
+}
 
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-			PgArchiverMain(0, NULL);
-			break;
-#endif
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-		default:
-			return (int) pgArchPid;
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
 	}
-
-	/* shouldn't get here */
-	return 0;
 }
 
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
 /*
- * pgarch_forkexec() -
+ *  PgArchIsSuppressed
  *
- * Format up the arglist for, then fork and exec, archive process
+ * Return true if archiver relaunch is suppressed.
+ *
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-static pid_t
-pgarch_forkexec(void)
+bool
+PgArchCanRestart(void)
 {
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
+	static time_t last_pgarch_start_time = 0;
+	time_t		curtime = time(NULL);
 
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
+	/*
+	 * allow to launch also for the first time and when something's wrong in
+	 * the time values.
+	 */
+	if (last_pgarch_start_time == 0 ||
+		curtime < last_pgarch_start_time ||
+		(curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL)
+	{
+		last_pgarch_start_time = curtime;
 
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
+		return true;
+	}
 
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our pgproc index so that backends can use our latch to wake
+	 * us up while we're sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int			arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will
+	 * be relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +246,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +284,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +306,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..e8af05c04e 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||			\
+	  (XLogArchivingAlways() &&									  \
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 PgArchCanRestart())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for
+		 * it to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and
+		 * syslogger processes are disregarded since they are not connected to
+		 * shared memory; we also disregard dead_end children here. Walsenders
+		 * and archiver are also disregarded, they will be terminated later
+		 * after writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..1e47a143e1 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchCanRestart(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_17_24_43_2021_866)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v53 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 227 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  74 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 137 insertions(+), 218 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..818c9a1f3f 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,70 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	   *latch;			/* latch to wake the archiver up */
+	slock_t		mutex;			/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	   *latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	/* fetching the latch pointer might not be atomic, so use spinlock */
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +213,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +251,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +273,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..460e629145 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3804,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3911,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_09_23_13_2021_947)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v54 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 241 +++++++++--------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 160 insertions(+), 217 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..8e572afea3 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,6 +71,12 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int		pgprocno;				/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
@@ -80,146 +84,79 @@
  */
 static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
+
+	return size;
+}
+
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
+
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
+
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
+	}
+}
 
 /*
- * pgarch_start
+ *  PgArchIsSuppressed
  *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
+ * Return true if archiver relaunch is suppressed.
  *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-int
-pgarch_start(void)
+bool
+PgArchIsSuppressed(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	time_t	curtime = time(NULL);
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+	if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL)
+		return true;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
 	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int	arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will be
+	 * relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +237,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +275,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +297,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..4f8e364284 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||	\
+	  (XLogArchivingAlways() &&									\
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 !PgArchIsSuppressed())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..640692d33e 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchIsSuppressed(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_13_49_06_2021_682)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v55 3/3] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 240 ++++++++++-------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 164 insertions(+), 212 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..07ba989a37 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,101 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int			pgprocno;		/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
-
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	Size		size = 0;
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	size = add_size(size, sizeof(PgArchData));
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
+	return size;
+}
 
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-			PgArchiverMain(0, NULL);
-			break;
-#endif
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-		default:
-			return (int) pgArchPid;
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
 	}
-
-	/* shouldn't get here */
-	return 0;
 }
 
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
 /*
- * pgarch_forkexec() -
+ *  PgArchIsSuppressed
  *
- * Format up the arglist for, then fork and exec, archive process
+ * Return true if archiver relaunch is suppressed.
+ *
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-static pid_t
-pgarch_forkexec(void)
+bool
+PgArchCanRestart(void)
 {
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
+	static time_t last_pgarch_start_time = 0;
+	time_t		curtime = time(NULL);
 
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
+	/*
+	 * allow to launch also for the first time and when something's wrong in
+	 * the time values.
+	 */
+	if (last_pgarch_start_time == 0 ||
+		curtime < last_pgarch_start_time ||
+		(curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL)
+	{
+		last_pgarch_start_time = curtime;
 
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
+		return true;
+	}
 
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our pgproc index so that backends can use our latch to wake
+	 * us up while we're sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int			arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will
+	 * be relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +246,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +284,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +306,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..e8af05c04e 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||			\
+	  (XLogArchivingAlways() &&									  \
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 PgArchCanRestart())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for
+		 * it to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and
+		 * syslogger processes are disregarded since they are not connected to
+		 * shared memory; we also disregard dead_end children here. Walsenders
+		 * and archiver are also disregarded, they will be terminated later
+		 * after writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..1e47a143e1 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchCanRestart(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_17_24_43_2021_866)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v53 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 227 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  74 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 137 insertions(+), 218 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..818c9a1f3f 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,70 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	   *latch;			/* latch to wake the archiver up */
+	slock_t		mutex;			/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	   *latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	/* fetching the latch pointer might not be atomic, so use spinlock */
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +213,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +251,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +273,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..460e629145 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3804,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3911,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_09_23_13_2021_947)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v53 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 227 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  74 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 137 insertions(+), 218 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..818c9a1f3f 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,70 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	   *latch;			/* latch to wake the archiver up */
+	slock_t		mutex;			/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	   *latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	/* fetching the latch pointer might not be atomic, so use spinlock */
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +213,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +251,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +273,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..460e629145 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3804,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3911,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_09_23_13_2021_947)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v53 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 227 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  74 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 137 insertions(+), 218 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..818c9a1f3f 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,70 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	   *latch;			/* latch to wake the archiver up */
+	slock_t		mutex;			/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	   *latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	/* fetching the latch pointer might not be atomic, so use spinlock */
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +213,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +251,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +273,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..460e629145 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3804,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3911,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_09_23_13_2021_947)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v54 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 241 +++++++++--------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 160 insertions(+), 217 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..8e572afea3 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,6 +71,12 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int		pgprocno;				/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
@@ -80,146 +84,79 @@
  */
 static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
+
+	return size;
+}
+
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
+
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
+
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
+	}
+}
 
 /*
- * pgarch_start
+ *  PgArchIsSuppressed
  *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
+ * Return true if archiver relaunch is suppressed.
  *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-int
-pgarch_start(void)
+bool
+PgArchIsSuppressed(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	time_t	curtime = time(NULL);
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+	if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL)
+		return true;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
 	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int	arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will be
+	 * relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +237,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +275,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +297,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..4f8e364284 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||	\
+	  (XLogArchivingAlways() &&									\
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 !PgArchIsSuppressed())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..640692d33e 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchIsSuppressed(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_13_49_06_2021_682)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v53 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 227 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  74 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 137 insertions(+), 218 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..818c9a1f3f 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,70 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	   *latch;			/* latch to wake the archiver up */
+	slock_t		mutex;			/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	   *latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	/* fetching the latch pointer might not be atomic, so use spinlock */
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +213,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +251,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +273,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..460e629145 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3804,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3911,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_09_23_13_2021_947)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v53 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 227 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  74 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 137 insertions(+), 218 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..818c9a1f3f 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,70 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	   *latch;			/* latch to wake the archiver up */
+	slock_t		mutex;			/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	   *latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	/* fetching the latch pointer might not be atomic, so use spinlock */
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +213,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +251,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +273,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..460e629145 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3804,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3911,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_09_23_13_2021_947)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v54 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 241 +++++++++--------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 160 insertions(+), 217 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..8e572afea3 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,6 +71,12 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int		pgprocno;				/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
@@ -80,146 +84,79 @@
  */
 static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
+
+	return size;
+}
+
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
+
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
+
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
+	}
+}
 
 /*
- * pgarch_start
+ *  PgArchIsSuppressed
  *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
+ * Return true if archiver relaunch is suppressed.
  *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-int
-pgarch_start(void)
+bool
+PgArchIsSuppressed(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	time_t	curtime = time(NULL);
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+	if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL)
+		return true;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
 	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int	arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will be
+	 * relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +237,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +275,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +297,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..4f8e364284 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||	\
+	  (XLogArchivingAlways() &&									\
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 !PgArchIsSuppressed())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..640692d33e 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchIsSuppressed(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_13_49_06_2021_682)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v55 3/3] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 240 ++++++++++-------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 164 insertions(+), 212 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..07ba989a37 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,101 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int			pgprocno;		/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
-
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	Size		size = 0;
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	size = add_size(size, sizeof(PgArchData));
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
+	return size;
+}
 
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-			PgArchiverMain(0, NULL);
-			break;
-#endif
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-		default:
-			return (int) pgArchPid;
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
 	}
-
-	/* shouldn't get here */
-	return 0;
 }
 
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
 /*
- * pgarch_forkexec() -
+ *  PgArchIsSuppressed
  *
- * Format up the arglist for, then fork and exec, archive process
+ * Return true if archiver relaunch is suppressed.
+ *
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-static pid_t
-pgarch_forkexec(void)
+bool
+PgArchCanRestart(void)
 {
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
+	static time_t last_pgarch_start_time = 0;
+	time_t		curtime = time(NULL);
 
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
+	/*
+	 * allow to launch also for the first time and when something's wrong in
+	 * the time values.
+	 */
+	if (last_pgarch_start_time == 0 ||
+		curtime < last_pgarch_start_time ||
+		(curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL)
+	{
+		last_pgarch_start_time = curtime;
 
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
+		return true;
+	}
 
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our pgproc index so that backends can use our latch to wake
+	 * us up while we're sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int			arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will
+	 * be relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +246,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +284,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +306,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..e8af05c04e 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||			\
+	  (XLogArchivingAlways() &&									  \
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 PgArchCanRestart())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for
+		 * it to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and
+		 * syslogger processes are disregarded since they are not connected to
+		 * shared memory; we also disregard dead_end children here. Walsenders
+		 * and archiver are also disregarded, they will be terminated later
+		 * after writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..1e47a143e1 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchCanRestart(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_17_24_43_2021_866)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v54 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 241 +++++++++--------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 160 insertions(+), 217 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..8e572afea3 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,6 +71,12 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int		pgprocno;				/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
@@ -80,146 +84,79 @@
  */
 static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
+
+	return size;
+}
+
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
+
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
+
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
+	}
+}
 
 /*
- * pgarch_start
+ *  PgArchIsSuppressed
  *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
+ * Return true if archiver relaunch is suppressed.
  *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-int
-pgarch_start(void)
+bool
+PgArchIsSuppressed(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	time_t	curtime = time(NULL);
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+	if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL)
+		return true;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
 	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int	arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will be
+	 * relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +237,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +275,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +297,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..4f8e364284 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||	\
+	  (XLogArchivingAlways() &&									\
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 !PgArchIsSuppressed())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..640692d33e 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchIsSuppressed(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_13_49_06_2021_682)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v55 3/3] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 240 ++++++++++-------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 164 insertions(+), 212 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..07ba989a37 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,101 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int			pgprocno;		/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
-
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	Size		size = 0;
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	size = add_size(size, sizeof(PgArchData));
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
+	return size;
+}
 
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-			PgArchiverMain(0, NULL);
-			break;
-#endif
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-		default:
-			return (int) pgArchPid;
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
 	}
-
-	/* shouldn't get here */
-	return 0;
 }
 
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
 /*
- * pgarch_forkexec() -
+ *  PgArchIsSuppressed
  *
- * Format up the arglist for, then fork and exec, archive process
+ * Return true if archiver relaunch is suppressed.
+ *
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-static pid_t
-pgarch_forkexec(void)
+bool
+PgArchCanRestart(void)
 {
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
+	static time_t last_pgarch_start_time = 0;
+	time_t		curtime = time(NULL);
 
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
+	/*
+	 * allow to launch also for the first time and when something's wrong in
+	 * the time values.
+	 */
+	if (last_pgarch_start_time == 0 ||
+		curtime < last_pgarch_start_time ||
+		(curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL)
+	{
+		last_pgarch_start_time = curtime;
 
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
+		return true;
+	}
 
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our pgproc index so that backends can use our latch to wake
+	 * us up while we're sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int			arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will
+	 * be relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +246,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +284,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +306,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..e8af05c04e 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||			\
+	  (XLogArchivingAlways() &&									  \
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 PgArchCanRestart())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for
+		 * it to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and
+		 * syslogger processes are disregarded since they are not connected to
+		 * shared memory; we also disregard dead_end children here. Walsenders
+		 * and archiver are also disregarded, they will be terminated later
+		 * after writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..1e47a143e1 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchCanRestart(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_17_24_43_2021_866)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v55 3/3] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 240 ++++++++++-------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 164 insertions(+), 212 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..07ba989a37 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,101 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int			pgprocno;		/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
-
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	Size		size = 0;
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	size = add_size(size, sizeof(PgArchData));
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
+	return size;
+}
 
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-			PgArchiverMain(0, NULL);
-			break;
-#endif
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-		default:
-			return (int) pgArchPid;
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
 	}
-
-	/* shouldn't get here */
-	return 0;
 }
 
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
 /*
- * pgarch_forkexec() -
+ *  PgArchIsSuppressed
  *
- * Format up the arglist for, then fork and exec, archive process
+ * Return true if archiver relaunch is suppressed.
+ *
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-static pid_t
-pgarch_forkexec(void)
+bool
+PgArchCanRestart(void)
 {
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
+	static time_t last_pgarch_start_time = 0;
+	time_t		curtime = time(NULL);
 
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
+	/*
+	 * allow to launch also for the first time and when something's wrong in
+	 * the time values.
+	 */
+	if (last_pgarch_start_time == 0 ||
+		curtime < last_pgarch_start_time ||
+		(curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL)
+	{
+		last_pgarch_start_time = curtime;
 
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
+		return true;
+	}
 
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our pgproc index so that backends can use our latch to wake
+	 * us up while we're sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int			arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will
+	 * be relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +246,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +284,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +306,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..e8af05c04e 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||			\
+	  (XLogArchivingAlways() &&									  \
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 PgArchCanRestart())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for
+		 * it to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and
+		 * syslogger processes are disregarded since they are not connected to
+		 * shared memory; we also disregard dead_end children here. Walsenders
+		 * and archiver are also disregarded, they will be terminated later
+		 * after writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..1e47a143e1 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchCanRestart(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_17_24_43_2021_866)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v53 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 227 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  74 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 137 insertions(+), 218 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..818c9a1f3f 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,70 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	   *latch;			/* latch to wake the archiver up */
+	slock_t		mutex;			/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	   *latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	/* fetching the latch pointer might not be atomic, so use spinlock */
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +213,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +251,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +273,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..460e629145 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3804,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3911,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_09_23_13_2021_947)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v54 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 241 +++++++++--------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 160 insertions(+), 217 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..8e572afea3 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,6 +71,12 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int		pgprocno;				/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
@@ -80,146 +84,79 @@
  */
 static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
+
+	return size;
+}
+
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
+
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
+
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
+	}
+}
 
 /*
- * pgarch_start
+ *  PgArchIsSuppressed
  *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
+ * Return true if archiver relaunch is suppressed.
  *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-int
-pgarch_start(void)
+bool
+PgArchIsSuppressed(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	time_t	curtime = time(NULL);
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+	if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL)
+		return true;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
 	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int	arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will be
+	 * relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +237,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +275,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +297,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..4f8e364284 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||	\
+	  (XLogArchivingAlways() &&									\
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 !PgArchIsSuppressed())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..640692d33e 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchIsSuppressed(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_13_49_06_2021_682)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v55 3/3] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 240 ++++++++++-------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 164 insertions(+), 212 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..07ba989a37 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,101 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int			pgprocno;		/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
-
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	Size		size = 0;
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	size = add_size(size, sizeof(PgArchData));
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
+	return size;
+}
 
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-			PgArchiverMain(0, NULL);
-			break;
-#endif
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-		default:
-			return (int) pgArchPid;
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
 	}
-
-	/* shouldn't get here */
-	return 0;
 }
 
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
 /*
- * pgarch_forkexec() -
+ *  PgArchIsSuppressed
  *
- * Format up the arglist for, then fork and exec, archive process
+ * Return true if archiver relaunch is suppressed.
+ *
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-static pid_t
-pgarch_forkexec(void)
+bool
+PgArchCanRestart(void)
 {
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
+	static time_t last_pgarch_start_time = 0;
+	time_t		curtime = time(NULL);
 
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
+	/*
+	 * allow to launch also for the first time and when something's wrong in
+	 * the time values.
+	 */
+	if (last_pgarch_start_time == 0 ||
+		curtime < last_pgarch_start_time ||
+		(curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL)
+	{
+		last_pgarch_start_time = curtime;
 
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
+		return true;
+	}
 
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our pgproc index so that backends can use our latch to wake
+	 * us up while we're sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int			arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will
+	 * be relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +246,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +284,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +306,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..e8af05c04e 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||			\
+	  (XLogArchivingAlways() &&									  \
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 PgArchCanRestart())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for
+		 * it to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and
+		 * syslogger processes are disregarded since they are not connected to
+		 * shared memory; we also disregard dead_end children here. Walsenders
+		 * and archiver are also disregarded, they will be terminated later
+		 * after writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..1e47a143e1 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchCanRestart(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_17_24_43_2021_866)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v54 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 241 +++++++++--------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 160 insertions(+), 217 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..8e572afea3 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,6 +71,12 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int		pgprocno;				/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
@@ -80,146 +84,79 @@
  */
 static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
+
+	return size;
+}
+
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
+
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
+
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
+	}
+}
 
 /*
- * pgarch_start
+ *  PgArchIsSuppressed
  *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
+ * Return true if archiver relaunch is suppressed.
  *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-int
-pgarch_start(void)
+bool
+PgArchIsSuppressed(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	time_t	curtime = time(NULL);
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+	if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL)
+		return true;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
 	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int	arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will be
+	 * relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +237,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +275,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +297,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..4f8e364284 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||	\
+	  (XLogArchivingAlways() &&									\
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 !PgArchIsSuppressed())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..640692d33e 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchIsSuppressed(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_13_49_06_2021_682)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v55 3/3] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 240 ++++++++++-------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 164 insertions(+), 212 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..07ba989a37 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,101 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int			pgprocno;		/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
-
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	Size		size = 0;
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	size = add_size(size, sizeof(PgArchData));
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
+	return size;
+}
 
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-			PgArchiverMain(0, NULL);
-			break;
-#endif
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-		default:
-			return (int) pgArchPid;
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
 	}
-
-	/* shouldn't get here */
-	return 0;
 }
 
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
 /*
- * pgarch_forkexec() -
+ *  PgArchIsSuppressed
  *
- * Format up the arglist for, then fork and exec, archive process
+ * Return true if archiver relaunch is suppressed.
+ *
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-static pid_t
-pgarch_forkexec(void)
+bool
+PgArchCanRestart(void)
 {
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
+	static time_t last_pgarch_start_time = 0;
+	time_t		curtime = time(NULL);
 
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
+	/*
+	 * allow to launch also for the first time and when something's wrong in
+	 * the time values.
+	 */
+	if (last_pgarch_start_time == 0 ||
+		curtime < last_pgarch_start_time ||
+		(curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL)
+	{
+		last_pgarch_start_time = curtime;
 
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
+		return true;
+	}
 
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our pgproc index so that backends can use our latch to wake
+	 * us up while we're sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int			arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will
+	 * be relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +246,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +284,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +306,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..e8af05c04e 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||			\
+	  (XLogArchivingAlways() &&									  \
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 PgArchCanRestart())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for
+		 * it to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and
+		 * syslogger processes are disregarded since they are not connected to
+		 * shared memory; we also disregard dead_end children here. Walsenders
+		 * and archiver are also disregarded, they will be terminated later
+		 * after writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..1e47a143e1 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchCanRestart(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_17_24_43_2021_866)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v54 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 241 +++++++++--------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 160 insertions(+), 217 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..8e572afea3 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,6 +71,12 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int		pgprocno;				/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
@@ -80,146 +84,79 @@
  */
 static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
+
+	return size;
+}
+
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
+
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
+
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
+	}
+}
 
 /*
- * pgarch_start
+ *  PgArchIsSuppressed
  *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
+ * Return true if archiver relaunch is suppressed.
  *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-int
-pgarch_start(void)
+bool
+PgArchIsSuppressed(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	time_t	curtime = time(NULL);
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+	if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL)
+		return true;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
 	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int	arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will be
+	 * relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +237,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +275,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +297,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..4f8e364284 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||	\
+	  (XLogArchivingAlways() &&									\
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 !PgArchIsSuppressed())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..640692d33e 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchIsSuppressed(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_13_49_06_2021_682)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v55 3/3] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 240 ++++++++++-------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 164 insertions(+), 212 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..07ba989a37 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,101 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int			pgprocno;		/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
-
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	Size		size = 0;
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	size = add_size(size, sizeof(PgArchData));
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
+	return size;
+}
 
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-			PgArchiverMain(0, NULL);
-			break;
-#endif
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-		default:
-			return (int) pgArchPid;
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
 	}
-
-	/* shouldn't get here */
-	return 0;
 }
 
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
 /*
- * pgarch_forkexec() -
+ *  PgArchIsSuppressed
  *
- * Format up the arglist for, then fork and exec, archive process
+ * Return true if archiver relaunch is suppressed.
+ *
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-static pid_t
-pgarch_forkexec(void)
+bool
+PgArchCanRestart(void)
 {
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
+	static time_t last_pgarch_start_time = 0;
+	time_t		curtime = time(NULL);
 
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
+	/*
+	 * allow to launch also for the first time and when something's wrong in
+	 * the time values.
+	 */
+	if (last_pgarch_start_time == 0 ||
+		curtime < last_pgarch_start_time ||
+		(curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL)
+	{
+		last_pgarch_start_time = curtime;
 
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
+		return true;
+	}
 
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our pgproc index so that backends can use our latch to wake
+	 * us up while we're sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int			arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will
+	 * be relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +246,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +284,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +306,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..e8af05c04e 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||			\
+	  (XLogArchivingAlways() &&									  \
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 PgArchCanRestart())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for
+		 * it to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and
+		 * syslogger processes are disregarded since they are not connected to
+		 * shared memory; we also disregard dead_end children here. Walsenders
+		 * and archiver are also disregarded, they will be terminated later
+		 * after writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..1e47a143e1 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchCanRestart(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_17_24_43_2021_866)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v53 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 227 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  74 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 137 insertions(+), 218 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..818c9a1f3f 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,70 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	   *latch;			/* latch to wake the archiver up */
+	slock_t		mutex;			/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	   *latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	/* fetching the latch pointer might not be atomic, so use spinlock */
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +213,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +251,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +273,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..460e629145 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3804,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3911,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_09_23_13_2021_947)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v54 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 241 +++++++++--------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 160 insertions(+), 217 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..8e572afea3 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,6 +71,12 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int		pgprocno;				/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
@@ -80,146 +84,79 @@
  */
 static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
+
+	return size;
+}
+
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
+
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
+
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
+	}
+}
 
 /*
- * pgarch_start
+ *  PgArchIsSuppressed
  *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
+ * Return true if archiver relaunch is suppressed.
  *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-int
-pgarch_start(void)
+bool
+PgArchIsSuppressed(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	time_t	curtime = time(NULL);
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+	if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL)
+		return true;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
 	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int	arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will be
+	 * relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +237,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +275,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +297,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..4f8e364284 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||	\
+	  (XLogArchivingAlways() &&									\
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 !PgArchIsSuppressed())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..640692d33e 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchIsSuppressed(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_13_49_06_2021_682)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v55 3/3] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 240 ++++++++++-------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 164 insertions(+), 212 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..07ba989a37 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,101 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int			pgprocno;		/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
-
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	Size		size = 0;
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	size = add_size(size, sizeof(PgArchData));
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
+	return size;
+}
 
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-			PgArchiverMain(0, NULL);
-			break;
-#endif
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-		default:
-			return (int) pgArchPid;
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
 	}
-
-	/* shouldn't get here */
-	return 0;
 }
 
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
 /*
- * pgarch_forkexec() -
+ *  PgArchIsSuppressed
  *
- * Format up the arglist for, then fork and exec, archive process
+ * Return true if archiver relaunch is suppressed.
+ *
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-static pid_t
-pgarch_forkexec(void)
+bool
+PgArchCanRestart(void)
 {
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
+	static time_t last_pgarch_start_time = 0;
+	time_t		curtime = time(NULL);
 
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
+	/*
+	 * allow to launch also for the first time and when something's wrong in
+	 * the time values.
+	 */
+	if (last_pgarch_start_time == 0 ||
+		curtime < last_pgarch_start_time ||
+		(curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL)
+	{
+		last_pgarch_start_time = curtime;
 
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
+		return true;
+	}
 
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our pgproc index so that backends can use our latch to wake
+	 * us up while we're sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int			arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will
+	 * be relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +246,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +284,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +306,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..e8af05c04e 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||			\
+	  (XLogArchivingAlways() &&									  \
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 PgArchCanRestart())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for
+		 * it to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and
+		 * syslogger processes are disregarded since they are not connected to
+		 * shared memory; we also disregard dead_end children here. Walsenders
+		 * and archiver are also disregarded, they will be terminated later
+		 * after writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..1e47a143e1 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchCanRestart(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_17_24_43_2021_866)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v53 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 227 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  74 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 137 insertions(+), 218 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..818c9a1f3f 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,70 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	   *latch;			/* latch to wake the archiver up */
+	slock_t		mutex;			/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	   *latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	/* fetching the latch pointer might not be atomic, so use spinlock */
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +213,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +251,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +273,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..460e629145 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3804,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3911,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_09_23_13_2021_947)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v54 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 241 +++++++++--------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 160 insertions(+), 217 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..8e572afea3 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,6 +71,12 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int		pgprocno;				/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
@@ -80,146 +84,79 @@
  */
 static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
+
+	return size;
+}
+
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
+
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
+
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
+	}
+}
 
 /*
- * pgarch_start
+ *  PgArchIsSuppressed
  *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
+ * Return true if archiver relaunch is suppressed.
  *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-int
-pgarch_start(void)
+bool
+PgArchIsSuppressed(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	time_t	curtime = time(NULL);
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+	if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL)
+		return true;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
 	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int	arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will be
+	 * relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +237,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +275,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +297,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..4f8e364284 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||	\
+	  (XLogArchivingAlways() &&									\
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 !PgArchIsSuppressed())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..640692d33e 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchIsSuppressed(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_13_49_06_2021_682)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v55 3/3] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 240 ++++++++++-------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 164 insertions(+), 212 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..07ba989a37 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,101 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int			pgprocno;		/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
-
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	Size		size = 0;
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	size = add_size(size, sizeof(PgArchData));
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
+	return size;
+}
 
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-			PgArchiverMain(0, NULL);
-			break;
-#endif
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-		default:
-			return (int) pgArchPid;
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
 	}
-
-	/* shouldn't get here */
-	return 0;
 }
 
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
 /*
- * pgarch_forkexec() -
+ *  PgArchIsSuppressed
  *
- * Format up the arglist for, then fork and exec, archive process
+ * Return true if archiver relaunch is suppressed.
+ *
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-static pid_t
-pgarch_forkexec(void)
+bool
+PgArchCanRestart(void)
 {
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
+	static time_t last_pgarch_start_time = 0;
+	time_t		curtime = time(NULL);
 
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
+	/*
+	 * allow to launch also for the first time and when something's wrong in
+	 * the time values.
+	 */
+	if (last_pgarch_start_time == 0 ||
+		curtime < last_pgarch_start_time ||
+		(curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL)
+	{
+		last_pgarch_start_time = curtime;
 
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
+		return true;
+	}
 
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our pgproc index so that backends can use our latch to wake
+	 * us up while we're sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int			arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will
+	 * be relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +246,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +284,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +306,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..e8af05c04e 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||			\
+	  (XLogArchivingAlways() &&									  \
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 PgArchCanRestart())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for
+		 * it to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and
+		 * syslogger processes are disregarded since they are not connected to
+		 * shared memory; we also disregard dead_end children here. Walsenders
+		 * and archiver are also disregarded, they will be terminated later
+		 * after writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..1e47a143e1 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchCanRestart(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_17_24_43_2021_866)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v54 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 241 +++++++++--------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 160 insertions(+), 217 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..8e572afea3 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,6 +71,12 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int		pgprocno;				/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
@@ -80,146 +84,79 @@
  */
 static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
+
+	return size;
+}
+
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
+
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
+
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
+	}
+}
 
 /*
- * pgarch_start
+ *  PgArchIsSuppressed
  *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
+ * Return true if archiver relaunch is suppressed.
  *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-int
-pgarch_start(void)
+bool
+PgArchIsSuppressed(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	time_t	curtime = time(NULL);
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+	if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL)
+		return true;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
 	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int	arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will be
+	 * relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +237,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +275,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +297,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..4f8e364284 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||	\
+	  (XLogArchivingAlways() &&									\
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 !PgArchIsSuppressed())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..640692d33e 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchIsSuppressed(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_13_49_06_2021_682)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v55 3/3] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 240 ++++++++++-------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 164 insertions(+), 212 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..07ba989a37 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,101 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int			pgprocno;		/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
-
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	Size		size = 0;
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	size = add_size(size, sizeof(PgArchData));
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
+	return size;
+}
 
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-			PgArchiverMain(0, NULL);
-			break;
-#endif
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-		default:
-			return (int) pgArchPid;
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
 	}
-
-	/* shouldn't get here */
-	return 0;
 }
 
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
 /*
- * pgarch_forkexec() -
+ *  PgArchIsSuppressed
  *
- * Format up the arglist for, then fork and exec, archive process
+ * Return true if archiver relaunch is suppressed.
+ *
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-static pid_t
-pgarch_forkexec(void)
+bool
+PgArchCanRestart(void)
 {
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
+	static time_t last_pgarch_start_time = 0;
+	time_t		curtime = time(NULL);
 
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
+	/*
+	 * allow to launch also for the first time and when something's wrong in
+	 * the time values.
+	 */
+	if (last_pgarch_start_time == 0 ||
+		curtime < last_pgarch_start_time ||
+		(curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL)
+	{
+		last_pgarch_start_time = curtime;
 
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
+		return true;
+	}
 
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our pgproc index so that backends can use our latch to wake
+	 * us up while we're sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int			arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will
+	 * be relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +246,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +284,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +306,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..e8af05c04e 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||			\
+	  (XLogArchivingAlways() &&									  \
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 PgArchCanRestart())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for
+		 * it to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and
+		 * syslogger processes are disregarded since they are not connected to
+		 * shared memory; we also disregard dead_end children here. Walsenders
+		 * and archiver are also disregarded, they will be terminated later
+		 * after writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..1e47a143e1 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchCanRestart(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_17_24_43_2021_866)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v53 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 227 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  74 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 137 insertions(+), 218 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..818c9a1f3f 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,70 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	   *latch;			/* latch to wake the archiver up */
+	slock_t		mutex;			/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	   *latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	/* fetching the latch pointer might not be atomic, so use spinlock */
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +213,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +251,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +273,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..460e629145 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3804,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3911,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_09_23_13_2021_947)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v54 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 241 +++++++++--------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 160 insertions(+), 217 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..8e572afea3 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,6 +71,12 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int		pgprocno;				/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
@@ -80,146 +84,79 @@
  */
 static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
+
+	return size;
+}
+
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
+
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
+
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
+	}
+}
 
 /*
- * pgarch_start
+ *  PgArchIsSuppressed
  *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
+ * Return true if archiver relaunch is suppressed.
  *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-int
-pgarch_start(void)
+bool
+PgArchIsSuppressed(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	time_t	curtime = time(NULL);
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+	if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL)
+		return true;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
 	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int	arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will be
+	 * relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +237,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +275,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +297,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..4f8e364284 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||	\
+	  (XLogArchivingAlways() &&									\
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 !PgArchIsSuppressed())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..640692d33e 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchIsSuppressed(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_13_49_06_2021_682)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v53 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 227 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  74 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 137 insertions(+), 218 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..818c9a1f3f 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,70 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	   *latch;			/* latch to wake the archiver up */
+	slock_t		mutex;			/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	   *latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	/* fetching the latch pointer might not be atomic, so use spinlock */
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +213,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +251,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +273,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..460e629145 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3804,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3911,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_09_23_13_2021_947)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v53 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 227 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  74 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 137 insertions(+), 218 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..818c9a1f3f 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,70 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	   *latch;			/* latch to wake the archiver up */
+	slock_t		mutex;			/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	   *latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	/* fetching the latch pointer might not be atomic, so use spinlock */
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +213,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +251,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +273,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..460e629145 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3804,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3911,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_09_23_13_2021_947)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v54 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 241 +++++++++--------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 160 insertions(+), 217 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..8e572afea3 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,6 +71,12 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int		pgprocno;				/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
@@ -80,146 +84,79 @@
  */
 static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
+
+	return size;
+}
+
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
+
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
+
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
+	}
+}
 
 /*
- * pgarch_start
+ *  PgArchIsSuppressed
  *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
+ * Return true if archiver relaunch is suppressed.
  *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-int
-pgarch_start(void)
+bool
+PgArchIsSuppressed(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	time_t	curtime = time(NULL);
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+	if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL)
+		return true;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
 	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int	arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will be
+	 * relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +237,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +275,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +297,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..4f8e364284 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||	\
+	  (XLogArchivingAlways() &&									\
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 !PgArchIsSuppressed())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..640692d33e 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchIsSuppressed(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_13_49_06_2021_682)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v55 3/3] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 240 ++++++++++-------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 164 insertions(+), 212 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..07ba989a37 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,101 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int			pgprocno;		/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
-
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	Size		size = 0;
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	size = add_size(size, sizeof(PgArchData));
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
+	return size;
+}
 
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-			PgArchiverMain(0, NULL);
-			break;
-#endif
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-		default:
-			return (int) pgArchPid;
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
 	}
-
-	/* shouldn't get here */
-	return 0;
 }
 
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
 /*
- * pgarch_forkexec() -
+ *  PgArchIsSuppressed
  *
- * Format up the arglist for, then fork and exec, archive process
+ * Return true if archiver relaunch is suppressed.
+ *
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-static pid_t
-pgarch_forkexec(void)
+bool
+PgArchCanRestart(void)
 {
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
+	static time_t last_pgarch_start_time = 0;
+	time_t		curtime = time(NULL);
 
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
+	/*
+	 * allow to launch also for the first time and when something's wrong in
+	 * the time values.
+	 */
+	if (last_pgarch_start_time == 0 ||
+		curtime < last_pgarch_start_time ||
+		(curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL)
+	{
+		last_pgarch_start_time = curtime;
 
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
+		return true;
+	}
 
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our pgproc index so that backends can use our latch to wake
+	 * us up while we're sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int			arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will
+	 * be relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +246,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +284,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +306,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..e8af05c04e 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||			\
+	  (XLogArchivingAlways() &&									  \
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 PgArchCanRestart())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for
+		 * it to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and
+		 * syslogger processes are disregarded since they are not connected to
+		 * shared memory; we also disregard dead_end children here. Walsenders
+		 * and archiver are also disregarded, they will be terminated later
+		 * after writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..1e47a143e1 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchCanRestart(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_17_24_43_2021_866)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v53 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 227 ++++++++---------------
 src/backend/postmaster/postmaster.c      |  74 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  13 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 137 insertions(+), 218 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..818c9a1f3f 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,70 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	Latch	   *latch;			/* latch to wake the archiver up */
+	slock_t		mutex;			/* locks this struct */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
 
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
-{
-	time_t		curtime;
-	pid_t		pgArchPid;
+	return size;
+}
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
+	if (!found)
 	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		SpinLockInit(&PgArch->mutex);
+		PgArch->latch = NULL;
 	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
 }
-#endif							/* EXEC_BACKEND */
-
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +146,49 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = MyLatch;
+	SpinLockRelease(&PgArch->mutex);
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	Latch	   *latch;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
+	/* fetching the latch pointer might not be atomic, so use spinlock */
+	SpinLockAcquire(&PgArch->mutex);
+	latch = PgArch->latch;
+	SpinLockRelease(&PgArch->mutex);
 
-	errno = save_errno;
+	if (latch)
+		SetLatch(latch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +213,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +251,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +273,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +659,17 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	SpinLockAcquire(&PgArch->mutex);
+	PgArch->latch = NULL;
+	SpinLockRelease(&PgArch->mutex);
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..460e629145 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -548,6 +548,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1793,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3008,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3143,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3406,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3612,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3804,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3911,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5037,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5134,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5188,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5429,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..d053bf1564 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,9 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_09_23_13_2021_947)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v54 3/7] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 241 +++++++++--------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 160 insertions(+), 217 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..8e572afea3 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,6 +71,12 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int		pgprocno;				/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
@@ -80,146 +84,79 @@
  */
 static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
+{
+	Size		size = 0;
 
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
+	size = add_size(size, sizeof(PgArchData));
+
+	return size;
+}
+
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
+
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
+
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
+	}
+}
 
 /*
- * pgarch_start
+ *  PgArchIsSuppressed
  *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
+ * Return true if archiver relaunch is suppressed.
  *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-int
-pgarch_start(void)
+bool
+PgArchIsSuppressed(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	time_t	curtime = time(NULL);
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
+	if ((curtime - last_pgarch_start_time) < PGARCH_RESTART_INTERVAL)
+		return true;
 
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
 	last_pgarch_start_time = curtime;
-
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
-
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
-
-			PgArchiverMain(0, NULL);
-			break;
-#endif
-
-		default:
-			return (int) pgArchPid;
-	}
-
-	/* shouldn't get here */
-	return 0;
-}
-
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
-/*
- * pgarch_forkexec() -
- *
- * Format up the arglist for, then fork and exec, archive process
- */
-static pid_t
-pgarch_forkexec(void)
-{
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
-
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
-
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
-
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +168,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our latch that backends can use to wake us up while we're
+	 * sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int	arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will be
+	 * relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +237,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +275,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +297,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +683,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..4f8e364284 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||	\
+	  (XLogArchivingAlways() &&									\
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 !PgArchIsSuppressed())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for it
+		 * to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and syslogger
+		 * processes are disregarded since they are not connected to shared
+		 * memory; we also disregard dead_end children here. Walsenders and
+		 * archiver are also disregarded, they will be terminated later after
+		 * writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..640692d33e 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchIsSuppressed(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_13_49_06_2021_682)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* [PATCH v55 3/3] Make archiver process an auxiliary process
@ 2021-03-11 09:01  Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Kyotaro Horiguchi @ 2021-03-11 09:01 UTC (permalink / raw)

This makes it possible to archiver process uses ipc functions and let
us monitor archiver process status.
---
 doc/src/sgml/monitoring.sgml             |   1 +
 src/backend/access/transam/xlogarchive.c |   4 +-
 src/backend/bootstrap/bootstrap.c        |  22 ++-
 src/backend/postmaster/pgarch.c          | 240 ++++++++++-------------
 src/backend/postmaster/postmaster.c      |  81 ++++----
 src/backend/storage/ipc/ipci.c           |   2 +
 src/include/miscadmin.h                  |   2 +
 src/include/postmaster/pgarch.h          |  14 +-
 src/include/storage/pmsignal.h           |   1 -
 src/include/storage/proc.h               |   8 +-
 src/tools/pgindent/typedefs.list         |   1 +
 11 files changed, 164 insertions(+), 212 deletions(-)

diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml
index 1ba813bbb9..a96455bdb2 100644
--- a/doc/src/sgml/monitoring.sgml
+++ b/doc/src/sgml/monitoring.sgml
@@ -935,6 +935,7 @@ postgres   27093  0.0  0.0  30096  2752 ?        Ss   11:34   0:00 postgres: ser
        <literal>logical replication worker</literal>,
        <literal>parallel worker</literal>, <literal>background writer</literal>,
        <literal>client backend</literal>, <literal>checkpointer</literal>,
+       <literal>archiver</literal>,
        <literal>startup</literal>, <literal>walreceiver</literal>,
        <literal>walsender</literal> and <literal>walwriter</literal>.
        In addition, background workers registered by extensions may have
diff --git a/src/backend/access/transam/xlogarchive.c b/src/backend/access/transam/xlogarchive.c
index 1c5a4f8b5a..26b023e754 100644
--- a/src/backend/access/transam/xlogarchive.c
+++ b/src/backend/access/transam/xlogarchive.c
@@ -25,11 +25,11 @@
 #include "common/archive.h"
 #include "miscadmin.h"
 #include "postmaster/startup.h"
+#include "postmaster/pgarch.h"
 #include "replication/walsender.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/lwlock.h"
-#include "storage/pmsignal.h"
 
 /*
  * Attempt to retrieve the specified file from off-line archival storage.
@@ -491,7 +491,7 @@ XLogArchiveNotify(const char *xlog)
 
 	/* Notify archiver that it's got something to do */
 	if (IsUnderPostmaster)
-		SendPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER);
+		PgArchWakeup();
 }
 
 /*
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index 6f615e6622..41da0c5059 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -317,6 +317,9 @@ AuxiliaryProcessMain(int argc, char *argv[])
 		case StartupProcess:
 			MyBackendType = B_STARTUP;
 			break;
+		case ArchiverProcess:
+			MyBackendType = B_ARCHIVER;
+			break;
 		case BgWriterProcess:
 			MyBackendType = B_BG_WRITER;
 			break;
@@ -437,30 +440,29 @@ AuxiliaryProcessMain(int argc, char *argv[])
 			proc_exit(1);		/* should never return */
 
 		case StartupProcess:
-			/* don't set signals, startup process has its own agenda */
 			StartupProcessMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
+
+		case ArchiverProcess:
+			PgArchiverMain();
+			proc_exit(1);
 
 		case BgWriterProcess:
-			/* don't set signals, bgwriter has its own agenda */
 			BackgroundWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case CheckpointerProcess:
-			/* don't set signals, checkpointer has its own agenda */
 			CheckpointerMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalWriterProcess:
-			/* don't set signals, walwriter has its own agenda */
 			InitXLOGAccess();
 			WalWriterMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		case WalReceiverProcess:
-			/* don't set signals, walreceiver has its own agenda */
 			WalReceiverMain();
-			proc_exit(1);		/* should never return */
+			proc_exit(1);
 
 		default:
 			elog(PANIC, "unrecognized process type: %d", (int) MyAuxProcType);
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index edec311f12..07ba989a37 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -38,16 +38,14 @@
 #include "libpq/pqsignal.h"
 #include "miscadmin.h"
 #include "pgstat.h"
-#include "postmaster/fork_process.h"
 #include "postmaster/interrupt.h"
 #include "postmaster/pgarch.h"
-#include "postmaster/postmaster.h"
-#include "storage/dsm.h"
 #include "storage/fd.h"
 #include "storage/ipc.h"
 #include "storage/latch.h"
-#include "storage/pg_shmem.h"
 #include "storage/pmsignal.h"
+#include "storage/procsignal.h"
+#include "storage/spin.h"
 #include "utils/guc.h"
 #include "utils/ps_status.h"
 
@@ -73,153 +71,101 @@
  */
 #define NUM_ORPHAN_CLEANUP_RETRIES 3
 
+/* Shared memory area for archiver process */
+typedef struct PgArchData
+{
+	int			pgprocno;		/* pgprocno of archiver process */
+} PgArchData;
+
 
 /* ----------
  * Local data
  * ----------
  */
-static time_t last_pgarch_start_time;
 static time_t last_sigterm_time = 0;
+static PgArchData *PgArch = NULL;
 
 /*
  * Flags set by interrupt handlers for later service in the main loop.
  */
-static volatile sig_atomic_t wakened = false;
 static volatile sig_atomic_t ready_to_stop = false;
 
 /* ----------
  * Local function forward declarations
  * ----------
  */
-#ifdef EXEC_BACKEND
-static pid_t pgarch_forkexec(void);
-#endif
-
-NON_EXEC_STATIC void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-static void pgarch_waken(SIGNAL_ARGS);
 static void pgarch_waken_stop(SIGNAL_ARGS);
 static void pgarch_MainLoop(void);
 static void pgarch_ArchiverCopyLoop(void);
 static bool pgarch_archiveXlog(char *xlog);
 static bool pgarch_readyXlog(char *xlog);
 static void pgarch_archiveDone(char *xlog);
+static void pgarch_die(int code, Datum arg);
 
-
-/* ------------------------------------------------------------
- * Public functions called from postmaster follow
- * ------------------------------------------------------------
- */
-
-/*
- * pgarch_start
- *
- *	Called from postmaster at startup or after an existing archiver
- *	died.  Attempt to fire up a fresh archiver process.
- *
- *	Returns PID of child process, or 0 if fail.
- *
- *	Note: if fail, we will be called again from the postmaster main loop.
- */
-int
-pgarch_start(void)
+/* Report shared memory space needed by PgArchShmemInit */
+Size
+PgArchShmemSize(void)
 {
-	time_t		curtime;
-	pid_t		pgArchPid;
+	Size		size = 0;
 
-	/*
-	 * Do nothing if no archiver needed
-	 */
-	if (!XLogArchivingActive())
-		return 0;
-
-	/*
-	 * Do nothing if too soon since last archiver start.  This is a safety
-	 * valve to protect against continuous respawn attempts if the archiver is
-	 * dying immediately at launch. Note that since we will be re-called from
-	 * the postmaster main loop, we will get another chance later.
-	 */
-	curtime = time(NULL);
-	if ((unsigned int) (curtime - last_pgarch_start_time) <
-		(unsigned int) PGARCH_RESTART_INTERVAL)
-		return 0;
-	last_pgarch_start_time = curtime;
+	size = add_size(size, sizeof(PgArchData));
 
-#ifdef EXEC_BACKEND
-	switch ((pgArchPid = pgarch_forkexec()))
-#else
-	switch ((pgArchPid = fork_process()))
-#endif
-	{
-		case -1:
-			ereport(LOG,
-					(errmsg("could not fork archiver: %m")));
-			return 0;
-
-#ifndef EXEC_BACKEND
-		case 0:
-			/* in postmaster child ... */
-			InitPostmasterChild();
-
-			/* Close the postmaster's sockets */
-			ClosePostmasterPorts(false);
+	return size;
+}
 
-			/* Drop our connection to postmaster's shared memory, as well */
-			dsm_detach_all();
-			PGSharedMemoryDetach();
+/* Allocate and initialize archiver-related shared memory */
+void
+PgArchShmemInit(void)
+{
+	bool		found;
 
-			PgArchiverMain(0, NULL);
-			break;
-#endif
+	PgArch = (PgArchData *)
+		ShmemInitStruct("Archiver Data", PgArchShmemSize(), &found);
 
-		default:
-			return (int) pgArchPid;
+	if (!found)
+	{
+		/* First time through, so initialize */
+		MemSet(PgArch, 0, PgArchShmemSize());
+		PgArch->pgprocno = INVALID_PGPROCNO;
 	}
-
-	/* shouldn't get here */
-	return 0;
 }
 
-/* ------------------------------------------------------------
- * Local functions called by archiver follow
- * ------------------------------------------------------------
- */
-
-
-#ifdef EXEC_BACKEND
-
 /*
- * pgarch_forkexec() -
+ *  PgArchIsSuppressed
  *
- * Format up the arglist for, then fork and exec, archive process
+ * Return true if archiver relaunch is suppressed.
+ *
+ * This is a safety valve to protect against continuous respawn attempts if the
+ * archiver is dying immediately at launch. Note that since we will retry to
+ * launch the archiver from the postmaster main loop, we will get another
+ * chance later.
  */
-static pid_t
-pgarch_forkexec(void)
+bool
+PgArchCanRestart(void)
 {
-	char	   *av[10];
-	int			ac = 0;
-
-	av[ac++] = "postgres";
+	static time_t last_pgarch_start_time = 0;
+	time_t		curtime = time(NULL);
 
-	av[ac++] = "--forkarch";
-
-	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
+	/*
+	 * allow to launch also for the first time and when something's wrong in
+	 * the time values.
+	 */
+	if (last_pgarch_start_time == 0 ||
+		curtime < last_pgarch_start_time ||
+		(curtime - last_pgarch_start_time) >= PGARCH_RESTART_INTERVAL)
+	{
+		last_pgarch_start_time = curtime;
 
-	av[ac] = NULL;
-	Assert(ac < lengthof(av));
+		return true;
+	}
 
-	return postmaster_forkexec(ac, av);
+	return false;
 }
-#endif							/* EXEC_BACKEND */
 
 
-/*
- * PgArchiverMain
- *
- *	The argc/argv parameters are valid only in EXEC_BACKEND case.  However,
- *	since we don't use 'em, it hardly matters...
- */
-NON_EXEC_STATIC void
-PgArchiverMain(int argc, char *argv[])
+/* Main entry point for archiver process */
+void
+PgArchiverMain(void)
 {
 	/*
 	 * Ignore all signals usually bound to some action in the postmaster,
@@ -231,33 +177,51 @@ PgArchiverMain(int argc, char *argv[])
 	/* SIGQUIT handler was already set up by InitPostmasterChild */
 	pqsignal(SIGALRM, SIG_IGN);
 	pqsignal(SIGPIPE, SIG_IGN);
-	pqsignal(SIGUSR1, pgarch_waken);
+	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
 	pqsignal(SIGUSR2, pgarch_waken_stop);
+
 	/* Reset some signals that are accepted by postmaster but not here */
 	pqsignal(SIGCHLD, SIG_DFL);
+
+	/* Unblock signals (they were blocked when the postmaster forked us) */
 	PG_SETMASK(&UnBlockSig);
 
-	MyBackendType = B_ARCHIVER;
-	init_ps_display(NULL);
+	/* We shouldn't be launched unnecessarily. */
+	Assert(XLogArchivingActive());
+
+	/* Arrange to clean up at archiver exit */
+	on_shmem_exit(pgarch_die, 0);
+
+	/*
+	 * Advertise our pgproc index so that backends can use our latch to wake
+	 * us up while we're sleeping.
+	 */
+	PgArch->pgprocno = MyProc->pgprocno;
 
 	pgarch_MainLoop();
 
-	exit(0);
+	proc_exit(0);
 }
 
-/* SIGUSR1 signal handler for archiver process */
-static void
-pgarch_waken(SIGNAL_ARGS)
+/*
+ * Wake up the archiver
+ */
+void
+PgArchWakeup(void)
 {
-	int			save_errno = errno;
+	int			arch_pgprocno = PgArch->pgprocno;
 
-	/* set flag that there is work to be done */
-	wakened = true;
-	SetLatch(MyLatch);
-
-	errno = save_errno;
+	/*
+	 * We don't acquire ProcArrayLock here.  It's actually fine because
+	 * procLatch isn't ever freed, so we just can potentially set the wrong
+	 * process' (or no process') latch.  Even in that case the archiver will
+	 * be relaunched shortly and will start archiving.
+	 */
+	if (arch_pgprocno != INVALID_PGPROCNO)
+		SetLatch(&ProcGlobal->allProcs[arch_pgprocno].procLatch);
 }
 
+
 /* SIGUSR2 signal handler for archiver process */
 static void
 pgarch_waken_stop(SIGNAL_ARGS)
@@ -282,14 +246,6 @@ pgarch_MainLoop(void)
 	pg_time_t	last_copy_time = 0;
 	bool		time_to_stop;
 
-	/*
-	 * We run the copy loop immediately upon entry, in case there are
-	 * unarchived files left over from a previous database run (or maybe the
-	 * archiver died unexpectedly).  After that we wait for a signal or
-	 * timeout before doing more.
-	 */
-	wakened = true;
-
 	/*
 	 * There shouldn't be anything for the archiver to do except to wait for a
 	 * signal ... however, the archiver exists to protect our data, so she
@@ -328,12 +284,8 @@ pgarch_MainLoop(void)
 		}
 
 		/* Do what we're here for */
-		if (wakened || time_to_stop)
-		{
-			wakened = false;
-			pgarch_ArchiverCopyLoop();
-			last_copy_time = time(NULL);
-		}
+		pgarch_ArchiverCopyLoop();
+		last_copy_time = time(NULL);
 
 		/*
 		 * Sleep until a signal is received, or until a poll is forced by
@@ -354,13 +306,9 @@ pgarch_MainLoop(void)
 							   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
 							   timeout * 1000L,
 							   WAIT_EVENT_ARCHIVER_MAIN);
-				if (rc & WL_TIMEOUT)
-					wakened = true;
 				if (rc & WL_POSTMASTER_DEATH)
 					time_to_stop = true;
 			}
-			else
-				wakened = true;
 		}
 
 		/*
@@ -744,3 +692,15 @@ pgarch_archiveDone(char *xlog)
 	StatusFilePath(rlogdone, xlog, ".done");
 	(void) durable_rename(rlogready, rlogdone, WARNING);
 }
+
+
+/*
+ * pgarch_die
+ *
+ * Exit-time cleanup handler
+ */
+static void
+pgarch_die(int code, Datum arg)
+{
+	PgArch->pgprocno = INVALID_PGPROCNO;
+}
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index edab95a19e..e8af05c04e 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,9 +443,10 @@ static void InitPostmasterDeathWatchHandle(void);
  * even during recovery.
  */
 #define PgArchStartupAllowed()	\
-	((XLogArchivingActive() && pmState == PM_RUN) ||	\
-	 (XLogArchivingAlways() &&	\
-	  (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY)))
+	(((XLogArchivingActive() && pmState == PM_RUN) ||			\
+	  (XLogArchivingAlways() &&									  \
+	   (pmState == PM_RECOVERY || pmState == PM_HOT_STANDBY))) && \
+	 PgArchCanRestart())
 
 #ifdef EXEC_BACKEND
 
@@ -548,6 +549,7 @@ static void ShmemBackendArrayRemove(Backend *bn);
 #endif							/* EXEC_BACKEND */
 
 #define StartupDataBase()		StartChildProcess(StartupProcess)
+#define StartArchiver()			StartChildProcess(ArchiverProcess)
 #define StartBackgroundWriter() StartChildProcess(BgWriterProcess)
 #define StartCheckpointer()		StartChildProcess(CheckpointerProcess)
 #define StartWalWriter()		StartChildProcess(WalWriterProcess)
@@ -1792,7 +1794,7 @@ ServerLoop(void)
 
 		/* If we have lost the archiver, try to start a new one. */
 		if (PgArchPID == 0 && PgArchStartupAllowed())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/* If we need to signal the autovacuum launcher, do so now */
 		if (avlauncher_needs_signal)
@@ -3007,7 +3009,7 @@ reaper(SIGNAL_ARGS)
 			if (!IsBinaryUpgrade && AutoVacuumingActive() && AutoVacPID == 0)
 				AutoVacPID = StartAutoVacLauncher();
 			if (PgArchStartupAllowed() && PgArchPID == 0)
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			if (PgStatPID == 0)
 				PgStatPID = pgstat_start();
 
@@ -3142,20 +3144,22 @@ reaper(SIGNAL_ARGS)
 		}
 
 		/*
-		 * Was it the archiver?  If so, just try to start a new one; no need
-		 * to force reset of the rest of the system.  (If fail, we'll try
-		 * again in future cycles of the main loop.).  Unless we were waiting
-		 * for it to shut down; don't restart it in that case, and
+		 * Was it the archiver?  If exit status is zero (normal) or one (FATAL
+		 * exit), we assume everything is all right just like normal backends
+		 * and just try to restart a new one so that we immediately retry
+		 * archiving remaining files. (If fail, we'll try again in future
+		 * cycles of the postmaster's main loop.) Unless we were waiting for
+		 * it to shut down; don't restart it in that case, and
 		 * PostmasterStateMachine() will advance to the next shutdown step.
 		 */
 		if (pid == PgArchPID)
 		{
 			PgArchPID = 0;
-			if (!EXIT_STATUS_0(exitstatus))
-				LogChildExit(LOG, _("archiver process"),
-							 pid, exitstatus);
+			if (!EXIT_STATUS_0(exitstatus) && !EXIT_STATUS_1(exitstatus))
+				HandleChildCrash(pid, exitstatus,
+								 _("archiver process"));
 			if (PgArchStartupAllowed())
-				PgArchPID = pgarch_start();
+				PgArchPID = StartArchiver();
 			continue;
 		}
 
@@ -3403,7 +3407,7 @@ CleanupBackend(int pid,
 
 /*
  * HandleChildCrash -- cleanup after failed backend, bgwriter, checkpointer,
- * walwriter, autovacuum, or background worker.
+ * walwriter, autovacuum, archiver or background worker.
  *
  * The objectives here are to clean up our local state about the child
  * process, and to signal all other remaining children to quickdie.
@@ -3609,19 +3613,16 @@ HandleChildCrash(int pid, int exitstatus, const char *procname)
 		signal_child(AutoVacPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
-	/*
-	 * Force a power-cycle of the pgarch process too.  (This isn't absolutely
-	 * necessary, but it seems like a good idea for robustness, and it
-	 * simplifies the state-machine logic in the case where a shutdown request
-	 * arrives during crash processing.)
-	 */
-	if (PgArchPID != 0 && take_action)
+	/* Take care of the archiver too */
+	if (pid == PgArchPID)
+		PgArchPID = 0;
+	else if (PgArchPID != 0 && take_action)
 	{
 		ereport(DEBUG2,
 				(errmsg_internal("sending %s to process %d",
-								 "SIGQUIT",
+								 (SendStop ? "SIGSTOP" : "SIGQUIT"),
 								 (int) PgArchPID)));
-		signal_child(PgArchPID, SIGQUIT);
+		signal_child(PgArchPID, (SendStop ? SIGSTOP : SIGQUIT));
 	}
 
 	/*
@@ -3804,12 +3805,11 @@ PostmasterStateMachine(void)
 		 * (including autovac workers), no bgworkers (including unconnected
 		 * ones), and no walwriter, autovac launcher or bgwriter.  If we are
 		 * doing crash recovery or an immediate shutdown then we expect the
-		 * checkpointer to exit as well, otherwise not. The archiver, stats,
-		 * and syslogger processes are disregarded since they are not
-		 * connected to shared memory; we also disregard dead_end children
-		 * here. Walsenders are also disregarded, they will be terminated
-		 * later after writing the checkpoint record, like the archiver
-		 * process.
+		 * checkpointer to exit as well, otherwise not. The stats and
+		 * syslogger processes are disregarded since they are not connected to
+		 * shared memory; we also disregard dead_end children here. Walsenders
+		 * and archiver are also disregarded, they will be terminated later
+		 * after writing the checkpoint record.
 		 */
 		if (CountChildren(BACKEND_TYPE_ALL - BACKEND_TYPE_WALSND) == 0 &&
 			StartupPID == 0 &&
@@ -3912,6 +3912,7 @@ PostmasterStateMachine(void)
 			Assert(CheckpointerPID == 0);
 			Assert(WalWriterPID == 0);
 			Assert(AutoVacPID == 0);
+			Assert(PgArchPID == 0);
 			/* syslogger is not considered here */
 			pmState = PM_NO_CHILDREN;
 		}
@@ -5037,12 +5038,6 @@ SubPostmasterMain(int argc, char *argv[])
 
 		StartBackgroundWorker();
 	}
-	if (strcmp(argv[1], "--forkarch") == 0)
-	{
-		/* Do not want to attach to shared memory */
-
-		PgArchiverMain(argc, argv); /* does not return */
-	}
 	if (strcmp(argv[1], "--forkcol") == 0)
 	{
 		/* Do not want to attach to shared memory */
@@ -5140,7 +5135,7 @@ sigusr1_handler(SIGNAL_ARGS)
 		 */
 		Assert(PgArchPID == 0);
 		if (XLogArchivingAlways())
-			PgArchPID = pgarch_start();
+			PgArchPID = StartArchiver();
 
 		/*
 		 * If we aren't planning to enter hot standby mode later, treat
@@ -5194,16 +5189,6 @@ sigusr1_handler(SIGNAL_ARGS)
 	if (StartWorkerNeeded || HaveCrashedWorker)
 		maybe_start_bgworkers();
 
-	if (CheckPostmasterSignal(PMSIGNAL_WAKEN_ARCHIVER) &&
-		PgArchPID != 0)
-	{
-		/*
-		 * Send SIGUSR1 to archiver process, to wake it up and begin archiving
-		 * next WAL file.
-		 */
-		signal_child(PgArchPID, SIGUSR1);
-	}
-
 	/* Tell syslogger to rotate logfile if requested */
 	if (SysLoggerPID != 0)
 	{
@@ -5445,6 +5430,10 @@ StartChildProcess(AuxProcType type)
 				ereport(LOG,
 						(errmsg("could not fork startup process: %m")));
 				break;
+			case ArchiverProcess:
+				ereport(LOG,
+						(errmsg("could not fork archiver process: %m")));
+				break;
 			case BgWriterProcess:
 				ereport(LOG,
 						(errmsg("could not fork background writer process: %m")));
diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c
index f9bbe97b50..3e4ec53a97 100644
--- a/src/backend/storage/ipc/ipci.c
+++ b/src/backend/storage/ipc/ipci.c
@@ -144,6 +144,7 @@ CreateSharedMemoryAndSemaphores(void)
 		size = add_size(size, ReplicationOriginShmemSize());
 		size = add_size(size, WalSndShmemSize());
 		size = add_size(size, WalRcvShmemSize());
+		size = add_size(size, PgArchShmemSize());
 		size = add_size(size, ApplyLauncherShmemSize());
 		size = add_size(size, SnapMgrShmemSize());
 		size = add_size(size, BTreeShmemSize());
@@ -258,6 +259,7 @@ CreateSharedMemoryAndSemaphores(void)
 	ReplicationOriginShmemInit();
 	WalSndShmemInit();
 	WalRcvShmemInit();
+	PgArchShmemInit();
 	ApplyLauncherShmemInit();
 
 	/*
diff --git a/src/include/miscadmin.h b/src/include/miscadmin.h
index 54693e047a..013850ac28 100644
--- a/src/include/miscadmin.h
+++ b/src/include/miscadmin.h
@@ -417,6 +417,7 @@ typedef enum
 	BootstrapProcess,
 	StartupProcess,
 	BgWriterProcess,
+	ArchiverProcess,
 	CheckpointerProcess,
 	WalWriterProcess,
 	WalReceiverProcess,
@@ -429,6 +430,7 @@ extern AuxProcType MyAuxProcType;
 #define AmBootstrapProcess()		(MyAuxProcType == BootstrapProcess)
 #define AmStartupProcess()			(MyAuxProcType == StartupProcess)
 #define AmBackgroundWriterProcess() (MyAuxProcType == BgWriterProcess)
+#define AmArchiverProcess()			(MyAuxProcType == ArchiverProcess)
 #define AmCheckpointerProcess()		(MyAuxProcType == CheckpointerProcess)
 #define AmWalWriterProcess()		(MyAuxProcType == WalWriterProcess)
 #define AmWalReceiverProcess()		(MyAuxProcType == WalReceiverProcess)
diff --git a/src/include/postmaster/pgarch.h b/src/include/postmaster/pgarch.h
index d102a21ab7..1e47a143e1 100644
--- a/src/include/postmaster/pgarch.h
+++ b/src/include/postmaster/pgarch.h
@@ -26,14 +26,10 @@
 #define MAX_XFN_CHARS	40
 #define VALID_XFN_CHARS "0123456789ABCDEF.history.backup.partial"
 
-/* ----------
- * Functions called from postmaster
- * ----------
- */
-extern int	pgarch_start(void);
-
-#ifdef EXEC_BACKEND
-extern void PgArchiverMain(int argc, char *argv[]) pg_attribute_noreturn();
-#endif
+extern Size PgArchShmemSize(void);
+extern void PgArchShmemInit(void);
+extern bool PgArchCanRestart(void);
+extern void PgArchiverMain(void) pg_attribute_noreturn();
+extern void PgArchWakeup(void);
 
 #endif							/* _PGARCH_H */
diff --git a/src/include/storage/pmsignal.h b/src/include/storage/pmsignal.h
index dbbed18f61..8ed4d87ae6 100644
--- a/src/include/storage/pmsignal.h
+++ b/src/include/storage/pmsignal.h
@@ -34,7 +34,6 @@ typedef enum
 {
 	PMSIGNAL_RECOVERY_STARTED,	/* recovery has started */
 	PMSIGNAL_BEGIN_HOT_STANDBY, /* begin Hot Standby */
-	PMSIGNAL_WAKEN_ARCHIVER,	/* send a NOTIFY signal to xlog archiver */
 	PMSIGNAL_ROTATE_LOGFILE,	/* send SIGUSR1 to syslogger to rotate logfile */
 	PMSIGNAL_START_AUTOVAC_LAUNCHER,	/* start an autovacuum launcher */
 	PMSIGNAL_START_AUTOVAC_WORKER,	/* start an autovacuum worker */
diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h
index a777cb64a1..2fd1ff09a7 100644
--- a/src/include/storage/proc.h
+++ b/src/include/storage/proc.h
@@ -370,11 +370,11 @@ extern PGPROC *PreparedXactProcs;
  * We set aside some extra PGPROC structures for auxiliary processes,
  * ie things that aren't full-fledged backends but need shmem access.
  *
- * Background writer, checkpointer and WAL writer run during normal operation.
- * Startup process and WAL receiver also consume 2 slots, but WAL writer is
- * launched only after startup has exited, so we only need 4 slots.
+ * Background writer, checkpointer, WAL writer and archiver run during normal
+ * operation.  Startup process and WAL receiver also consume 2 slots, but WAL
+ * writer is launched only after startup has exited, so we only need 5 slots.
  */
-#define NUM_AUXILIARY_PROCS		4
+#define NUM_AUXILIARY_PROCS		5
 
 /* configurable options */
 extern PGDLLIMPORT int DeadlockTimeout;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 99a34be465..78e852569e 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -1572,6 +1572,7 @@ PGresAttValue
 PGresParamDesc
 PGresult
 PGresult_data
+PgArchData
 PHANDLE
 PLAINTREE
 PLUID_AND_ATTRIBUTES
-- 
2.27.0


----Next_Part(Fri_Mar_12_17_24_43_2021_866)----





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* RFC: Allow EXPLAIN to Output Page Fault Information
@ 2024-12-24 08:53  torikoshia <[email protected]>
  0 siblings, 1 reply; 283+ messages in thread

From: torikoshia @ 2024-12-24 08:53 UTC (permalink / raw)
  To: pgsql-hackers

Hi,

When reading the output of EXPLAIN (ANALYZE) to diagnose slow queries 
for our customers, I often want to know how many page faults occurred, 
especially major page faults, which involve disk access.

Currently, the BUFFERS option in EXPLAIN provides information on whether 
a page was found in the shared buffers, but it doesn't provide insight 
into whether the page was found in the OS cache or not and disk I/O 
occurred.

Since page faults especially major one impact performance compared to 
shared buffer and OS cache hits, it would be helpful to track these 
events.

I have attached a PoC patch that modifies EXPLAIN to include page fault 
information during both the planning and execution phases of a query. 
The output would look like this:

   =# EXPLAIN (ANALYZE, PAGEFAULTS)
           SELECT * FROM pgbench_branches b
             JOIN pgbench_accounts a ON b.bid = a.bid ORDER BY a.aid;

   QUERY PLAN
   
---------------------------------------------------------------------------------------------------------------------------------------------------------------------
     Nested Loop  (cost=0.58..335386.98 rows=4999917 width=197) (actual 
time=3.785..5590.294 rows=5000000 loops=1)

       ... (omitted)

     Planning:
       Buffers: shared hit=50 read=48 dirtied=4 written=2
       Page Faults: minor=30 major=19 <-ADDED
     Planning Time: 22.080 ms
     Execution:
       Page Faults: minor=49 major=5 <-ADDED
     Execution Time: 5794.356 ms

The patch has not yet added this functionality to auto_explain, but I 
believe this feature would be more useful in auto_explain than in the 
EXPLAIN command itself. I plan to add it to auto_explain if there's 
interest in including page fault information in EXPLAIN.

While GUCs like log_statement_stats allow logging of getrusage(2) 
information, including page faults, always enabling this can lead to 
excessive log output. It would be better to log this data only when 
queries are slow. Therefore, adding this feature to auto_explain seems 
like a good solution.


The patch introduces a new option, PAGEFAULTS, but it may be more 
appropriate to include the page fault information in another option, 
such as SUMMARY, especially if there are other useful resources that can 
be obtained from getrusage(2).


The patch cannot be applied to Windows because getrusage() in PostgreSQL 
ported for Windows currently only tracks CPU times. I'm not sure if 
information on major and minor page faults is accessible on Windows, but 
it might be acceptable to treat it similarly to log_statement_stats and 
exclude it from Windows support.


I also tried to add page faults information for each plan node, similar 
to the BUFFERS option, but I decided against this approach due to the 
performance impact. The frequent calls to getrusage(2), i.e. each time 
getting one row, created significant overhead.


Any feedback would be greatly appreciated.


-- 
Regards,

--
Atsushi Torikoshi
Seconded from NTT DATA GROUP CORPORATION to SRA OSS K.K.

Attachments:

  [text/x-diff] v1-0001-PoC-Allow-EXPLAIN-to-output-page-fault-info.patch (10.6K, ../../[email protected]/2-v1-0001-PoC-Allow-EXPLAIN-to-output-page-fault-info.patch)
  download | inline diff:
From 8c28ec288a99233580b15ae689e81610b2a8348c Mon Sep 17 00:00:00 2001
From: Atsushi Torikoshi <[email protected]>
Date: Tue, 24 Dec 2024 17:26:18 +0900
Subject: [PATCH v1] PoC: Allow EXPLAIN to output page fault information

This patch adds PAGEFAULTS option to EXPLAIN and it tracks both
minor and major faults during planning and execution phases.

This is a PoC patch and only shows page faults when the FORMAT is TEXT.

---
 src/backend/commands/explain.c | 103 +++++++++++++++++++++++++++++++--
 src/backend/commands/prepare.c |  23 ++++++++
 src/include/commands/explain.h |  11 ++++
 3 files changed, 133 insertions(+), 4 deletions(-)

diff --git a/src/backend/commands/explain.c b/src/backend/commands/explain.c
index a201ed3082..b8943c7ef9 100644
--- a/src/backend/commands/explain.c
+++ b/src/backend/commands/explain.c
@@ -13,6 +13,8 @@
  */
 #include "postgres.h"
 
+#include <sys/resource.h>
+
 #include "access/xact.h"
 #include "catalog/pg_type.h"
 #include "commands/createas.h"
@@ -145,6 +147,8 @@ static void show_foreignscan_info(ForeignScanState *fsstate, ExplainState *es);
 static const char *explain_get_index_name(Oid indexId);
 static bool peek_buffer_usage(ExplainState *es, const BufferUsage *usage);
 static void show_buffer_usage(ExplainState *es, const BufferUsage *usage);
+static bool peek_pagefault(ExplainState *es, const PageFaults * usage);
+static void show_pagefault(ExplainState *es, const PageFaults * usage);
 static void show_wal_usage(ExplainState *es, const WalUsage *usage);
 static void show_memory_counters(ExplainState *es,
 								 const MemoryContextCounters *mem_counters);
@@ -217,6 +221,8 @@ ExplainQuery(ParseState *pstate, ExplainStmt *stmt,
 			buffers_set = true;
 			es->buffers = defGetBoolean(opt);
 		}
+		else if (strcmp(opt->defname, "pagefaults") == 0)
+			es->pagefaults = defGetBoolean(opt);
 		else if (strcmp(opt->defname, "wal") == 0)
 			es->wal = defGetBoolean(opt);
 		else if (strcmp(opt->defname, "settings") == 0)
@@ -475,6 +481,8 @@ standard_ExplainOneQuery(Query *query, int cursorOptions,
 				planduration;
 	BufferUsage bufusage_start,
 				bufusage;
+	PageFaults	pagefaults = {0};
+	PageFaults	pagefaults_start = {0};
 	MemoryContextCounters mem_counters;
 	MemoryContext planner_ctx = NULL;
 	MemoryContext saved_ctx = NULL;
@@ -499,6 +507,15 @@ standard_ExplainOneQuery(Query *query, int cursorOptions,
 		bufusage_start = pgBufferUsage;
 	INSTR_TIME_SET_CURRENT(planstart);
 
+	if (es->pagefaults)
+	{
+		struct rusage rusage;
+
+		getrusage(RUSAGE_SELF, &rusage);
+		pagefaults_start.minflt = rusage.ru_minflt;
+		pagefaults_start.majflt = rusage.ru_majflt;
+	}
+
 	/* plan the query */
 	plan = pg_plan_query(query, queryString, cursorOptions, params);
 
@@ -518,9 +535,19 @@ standard_ExplainOneQuery(Query *query, int cursorOptions,
 		BufferUsageAccumDiff(&bufusage, &pgBufferUsage, &bufusage_start);
 	}
 
+	if (es->pagefaults)
+	{
+		struct rusage rusage;
+
+		getrusage(RUSAGE_SELF, &rusage);
+		pagefaults.minflt = rusage.ru_minflt - pagefaults_start.minflt;
+		pagefaults.majflt = rusage.ru_majflt - pagefaults_start.majflt;
+	}
+
 	/* run it (if needed) and produce output */
 	ExplainOnePlan(plan, into, es, queryString, params, queryEnv,
 				   &planduration, (es->buffers ? &bufusage : NULL),
+				   (es->pagefaults ? &pagefaults : NULL),
 				   es->memory ? &mem_counters : NULL);
 }
 
@@ -644,7 +671,7 @@ void
 ExplainOnePlan(PlannedStmt *plannedstmt, IntoClause *into, ExplainState *es,
 			   const char *queryString, ParamListInfo params,
 			   QueryEnvironment *queryEnv, const instr_time *planduration,
-			   const BufferUsage *bufusage,
+			   const BufferUsage *bufusage, const PageFaults * planpagefaults,
 			   const MemoryContextCounters *mem_counters)
 {
 	DestReceiver *dest;
@@ -654,6 +681,9 @@ ExplainOnePlan(PlannedStmt *plannedstmt, IntoClause *into, ExplainState *es,
 	int			eflags;
 	int			instrument_option = 0;
 	SerializeMetrics serializeMetrics = {0};
+	PageFaults	pagefaults = {0};
+	PageFaults	pagefaults_start = {0};
+	struct rusage rusage;
 
 	Assert(plannedstmt->commandType != CMD_UTILITY);
 
@@ -674,6 +704,14 @@ ExplainOnePlan(PlannedStmt *plannedstmt, IntoClause *into, ExplainState *es,
 	 */
 	INSTR_TIME_SET_CURRENT(starttime);
 
+	if (es->pagefaults)
+	{
+		getrusage(RUSAGE_SELF, &rusage);
+
+		pagefaults_start.minflt = rusage.ru_minflt;
+		pagefaults_start.majflt = rusage.ru_majflt;
+	}
+
 	/*
 	 * Use a snapshot with an updated command ID to ensure this query sees
 	 * results of any previously executed queries.
@@ -748,7 +786,8 @@ ExplainOnePlan(PlannedStmt *plannedstmt, IntoClause *into, ExplainState *es,
 	ExplainPrintPlan(es, queryDesc);
 
 	/* Show buffer and/or memory usage in planning */
-	if (peek_buffer_usage(es, bufusage) || mem_counters)
+	if (peek_buffer_usage(es, bufusage) || peek_pagefault(es, planpagefaults) ||
+		mem_counters)
 	{
 		ExplainOpenGroup("Planning", "Planning", true, es);
 
@@ -758,10 +797,12 @@ ExplainOnePlan(PlannedStmt *plannedstmt, IntoClause *into, ExplainState *es,
 			appendStringInfoString(es->str, "Planning:\n");
 			es->indent++;
 		}
-
 		if (bufusage)
 			show_buffer_usage(es, bufusage);
 
+		if (es->pagefaults)
+			show_pagefault(es, planpagefaults);
+
 		if (mem_counters)
 			show_memory_counters(es, mem_counters);
 
@@ -813,6 +854,26 @@ ExplainOnePlan(PlannedStmt *plannedstmt, IntoClause *into, ExplainState *es,
 
 	totaltime += elapsed_time(&starttime);
 
+	if (es->pagefaults)
+	{
+		getrusage(RUSAGE_SELF, &rusage);
+
+		pagefaults.minflt = rusage.ru_minflt - pagefaults_start.minflt;
+		pagefaults.majflt = rusage.ru_majflt - pagefaults_start.majflt;
+
+		if (es->format == EXPLAIN_FORMAT_TEXT)
+		{
+			ExplainIndentText(es);
+			appendStringInfoString(es->str, "Execution:\n");
+			es->indent++;
+		}
+		show_pagefault(es, &pagefaults);
+
+		if (es->format == EXPLAIN_FORMAT_TEXT)
+			es->indent--;
+		ExplainCloseGroup("Execution", "Execution", true, es);
+	}
+
 	/*
 	 * We only report execution time if we actually ran the query (that is,
 	 * the user specified ANALYZE), and if summary reporting is enabled (the
@@ -822,7 +883,6 @@ ExplainOnePlan(PlannedStmt *plannedstmt, IntoClause *into, ExplainState *es,
 	if (es->summary && es->analyze)
 		ExplainPropertyFloat("Execution Time", "ms", 1000.0 * totaltime, 3,
 							 es);
-
 	ExplainCloseGroup("Query", NULL, true, es);
 }
 
@@ -4232,6 +4292,41 @@ show_buffer_usage(ExplainState *es, const BufferUsage *usage)
 	}
 }
 
+static bool
+peek_pagefault(ExplainState *es, const PageFaults * usage)
+{
+	if (usage == NULL)
+		return false;
+
+	if (usage->minflt <= 0 && usage->majflt <= 0)
+		return false;
+
+	else
+		return true;
+}
+
+/*
+ * Show majar/minor page faults.
+ */
+static void
+show_pagefault(ExplainState *es, const PageFaults * usage)
+{
+	/* Show only positive counter values. */
+	if (usage->minflt <= 0 && usage->majflt <= 0)
+		return;
+
+	if (es->format == EXPLAIN_FORMAT_TEXT)
+	{
+
+		ExplainIndentText(es);
+		appendStringInfoString(es->str, "Page Faults:");
+		appendStringInfo(es->str, " minor=%ld", (long) usage->minflt);
+		appendStringInfo(es->str, " major=%ld", (long) usage->majflt);
+
+		appendStringInfoChar(es->str, '\n');
+	}
+}
+
 /*
  * Show WAL usage details.
  */
diff --git a/src/backend/commands/prepare.c b/src/backend/commands/prepare.c
index 39a71c1de2..4d944aaeb4 100644
--- a/src/backend/commands/prepare.c
+++ b/src/backend/commands/prepare.c
@@ -17,6 +17,7 @@
 #include "postgres.h"
 
 #include <limits.h>
+#include <sys/resource.h>
 
 #include "access/xact.h"
 #include "catalog/pg_type.h"
@@ -579,6 +580,8 @@ ExplainExecuteQuery(ExecuteStmt *execstmt, IntoClause *into, ExplainState *es,
 	instr_time	planduration;
 	BufferUsage bufusage_start,
 				bufusage;
+	PageFaults	pagefaults_start,
+				pagefaults;
 	MemoryContextCounters mem_counters;
 	MemoryContext planner_ctx = NULL;
 	MemoryContext saved_ctx = NULL;
@@ -595,6 +598,16 @@ ExplainExecuteQuery(ExecuteStmt *execstmt, IntoClause *into, ExplainState *es,
 
 	if (es->buffers)
 		bufusage_start = pgBufferUsage;
+
+	if (es->pagefaults)
+	{
+		struct rusage rusage;
+
+		getrusage(RUSAGE_SELF, &rusage);
+		pagefaults_start.minflt = rusage.ru_minflt;
+		pagefaults_start.majflt = rusage.ru_majflt;
+	}
+
 	INSTR_TIME_SET_CURRENT(planstart);
 
 	/* Look it up in the hash table */
@@ -646,6 +659,15 @@ ExplainExecuteQuery(ExecuteStmt *execstmt, IntoClause *into, ExplainState *es,
 		BufferUsageAccumDiff(&bufusage, &pgBufferUsage, &bufusage_start);
 	}
 
+	if (es->pagefaults)
+	{
+		struct rusage rusage;
+
+		getrusage(RUSAGE_SELF, &rusage);
+		pagefaults.minflt = rusage.ru_minflt - pagefaults_start.minflt;
+		pagefaults.majflt = rusage.ru_majflt - pagefaults_start.majflt;
+	}
+
 	plan_list = cplan->stmt_list;
 
 	/* Explain each query */
@@ -656,6 +678,7 @@ ExplainExecuteQuery(ExecuteStmt *execstmt, IntoClause *into, ExplainState *es,
 		if (pstmt->commandType != CMD_UTILITY)
 			ExplainOnePlan(pstmt, into, es, query_string, paramLI, pstate->p_queryEnv,
 						   &planduration, (es->buffers ? &bufusage : NULL),
+						   (es->pagefaults ? &pagefaults : NULL),
 						   es->memory ? &mem_counters : NULL);
 		else
 			ExplainOneUtility(pstmt->utilityStmt, into, es, pstate, paramLI);
diff --git a/src/include/commands/explain.h b/src/include/commands/explain.h
index aa5872bc15..dd95e0447c 100644
--- a/src/include/commands/explain.h
+++ b/src/include/commands/explain.h
@@ -49,6 +49,7 @@ typedef struct ExplainState
 	bool		analyze;		/* print actual times */
 	bool		costs;			/* print estimated costs */
 	bool		buffers;		/* print buffer usage */
+	bool		pagefaults;		/* print pagefaults */
 	bool		wal;			/* print WAL usage */
 	bool		timing;			/* print detailed node timing */
 	bool		summary;		/* print total planning and execution timing */
@@ -73,6 +74,15 @@ typedef struct ExplainState
 	ExplainWorkersState *workers_state; /* needed if parallel plan */
 } ExplainState;
 
+typedef struct PageFaults
+{
+	long		minflt;			/* # of page faults which were serviced
+								 * without requiring any I/O */
+	long		majflt;			/* # of page faults which were serviced by
+								 * doing I/O */
+}			PageFaults;
+
+
 /* Hook for plugins to get control in ExplainOneQuery() */
 typedef void (*ExplainOneQuery_hook_type) (Query *query,
 										   int cursorOptions,
@@ -108,6 +118,7 @@ extern void ExplainOnePlan(PlannedStmt *plannedstmt, IntoClause *into,
 						   ParamListInfo params, QueryEnvironment *queryEnv,
 						   const instr_time *planduration,
 						   const BufferUsage *bufusage,
+						   const PageFaults * planpagefaults,
 						   const MemoryContextCounters *mem_counters);
 
 extern void ExplainPrintPlan(ExplainState *es, QueryDesc *queryDesc);

base-commit: 6f3820f37aba94232468365bae7ba5de697fe993
-- 
2.39.2



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* Re: RFC: Allow EXPLAIN to Output Page Fault Information
@ 2026-05-21 05:38  vellaipandiyan sm <[email protected]>
  parent: torikoshia <[email protected]>
  0 siblings, 1 reply; 283+ messages in thread

From: vellaipandiyan sm @ 2026-05-21 05:38 UTC (permalink / raw)
  To: torikoshia <[email protected]>; +Cc: pgsql-hackers

Hello hackers,

I reviewed the EXPLAIN storage I/O patch and the overall direction seems
useful, especially for distinguishing shared-buffer hits from actual
storage reads during query analysis.

One concern that stood out to me from the later discussion is the
interaction with asynchronous I/O and worker-based I/O accounting.

Since the patch currently relies on per-process getrusage() statistics, it
seems possible that the reported values could become partial or misleading
once I/O is performed outside the backend process context. In particular,
worker-based AIO could undercount storage reads/writes while still
returning non-zero values, which may make the output appear more accurate
than it actually is.

I also wonder whether this should affect the semantics/documentation of the
feature itself — i.e. whether the reported numbers should be described more
explicitly as “backend-observed synchronous storage I/O” rather than total
query I/O.

That said, the examples showing differences between OS cache hits and
actual storage reads were quite compelling, especially for query
performance debugging.

Thanks for working on the patch.

Regards,
Vellaipandiyan

On Thu, May 21, 2026 at 11:07 AM torikoshia <[email protected]>
wrote:

> Hi,
>
> When reading the output of EXPLAIN (ANALYZE) to diagnose slow queries
> for our customers, I often want to know how many page faults occurred,
> especially major page faults, which involve disk access.
>
> Currently, the BUFFERS option in EXPLAIN provides information on whether
> a page was found in the shared buffers, but it doesn't provide insight
> into whether the page was found in the OS cache or not and disk I/O
> occurred.
>
> Since page faults especially major one impact performance compared to
> shared buffer and OS cache hits, it would be helpful to track these
> events.
>
> I have attached a PoC patch that modifies EXPLAIN to include page fault
> information during both the planning and execution phases of a query.
> The output would look like this:
>
>    =# EXPLAIN (ANALYZE, PAGEFAULTS)
>            SELECT * FROM pgbench_branches b
>              JOIN pgbench_accounts a ON b.bid = a.bid ORDER BY a.aid;
>
>    QUERY PLAN
>
>
> ---------------------------------------------------------------------------------------------------------------------------------------------------------------------
>      Nested Loop  (cost=0.58..335386.98 rows=4999917 width=197) (actual
> time=3.785..5590.294 rows=5000000 loops=1)
>
>        ... (omitted)
>
>      Planning:
>        Buffers: shared hit=50 read=48 dirtied=4 written=2
>        Page Faults: minor=30 major=19 <-ADDED
>      Planning Time: 22.080 ms
>      Execution:
>        Page Faults: minor=49 major=5 <-ADDED
>      Execution Time: 5794.356 ms
>
> The patch has not yet added this functionality to auto_explain, but I
> believe this feature would be more useful in auto_explain than in the
> EXPLAIN command itself. I plan to add it to auto_explain if there's
> interest in including page fault information in EXPLAIN.
>
> While GUCs like log_statement_stats allow logging of getrusage(2)
> information, including page faults, always enabling this can lead to
> excessive log output. It would be better to log this data only when
> queries are slow. Therefore, adding this feature to auto_explain seems
> like a good solution.
>
>
> The patch introduces a new option, PAGEFAULTS, but it may be more
> appropriate to include the page fault information in another option,
> such as SUMMARY, especially if there are other useful resources that can
> be obtained from getrusage(2).
>
>
> The patch cannot be applied to Windows because getrusage() in PostgreSQL
> ported for Windows currently only tracks CPU times. I'm not sure if
> information on major and minor page faults is accessible on Windows, but
> it might be acceptable to treat it similarly to log_statement_stats and
> exclude it from Windows support.
>
>
> I also tried to add page faults information for each plan node, similar
> to the BUFFERS option, but I decided against this approach due to the
> performance impact. The frequent calls to getrusage(2), i.e. each time
> getting one row, created significant overhead.
>
>
> Any feedback would be greatly appreciated.
>
>
> --
> Regards,
>
> --
> Atsushi Torikoshi
> Seconded from NTT DATA GROUP CORPORATION to SRA OSS K.K.


^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* Re: RFC: Allow EXPLAIN to Output Page Fault Information
@ 2026-05-22 16:07  Atsushi Torikoshi <[email protected]>
  parent: vellaipandiyan sm <[email protected]>
  0 siblings, 2 replies; 283+ messages in thread

From: Atsushi Torikoshi @ 2026-05-22 16:07 UTC (permalink / raw)
  To: vellaipandiyan sm <[email protected]>; +Cc: torikoshia <[email protected]>; pgsql-hackers

Thanks for the review!

On Thu, May 21, 2026 at 2:38 PM vellaipandiyan sm
<[email protected]> wrote:
>
> Hello hackers,
>
> I reviewed the EXPLAIN storage I/O patch and the overall direction seems useful, especially for distinguishing shared-buffer hits from actual storage reads during query analysis.
>
> One concern that stood out to me from the later discussion is the interaction with asynchronous I/O and worker-based I/O accounting.
>
> Since the patch currently relies on per-process getrusage() statistics, it seems possible that the reported values could become partial or misleading once I/O is performed outside the backend process context. In particular, worker-based AIO could undercount storage reads/writes while still returning non-zero values, which may make the output appear more accurate than it actually is.

Yeah, to avoid reporting the misleadingly underestimated values, no
output is shown when worker-based AIO is used, as described in the
docs:

+ ..Also, when
+ <xref linkend="guc-io-method"/> is set to <literal>worker</literal>, no output
+ will be shown, as I/O handled by asynchronous workers cannot be measured
+ accurately.

> I also wonder whether this should affect the semantics/documentation of the feature itself — i.e. whether the reported numbers should be described more explicitly as “backend-observed synchronous storage I/O” rather than total query I/O.

Updated the patch to clarify that the reported values include not only
the backend process executing the query, but also any parallel query
worker processes involved in the query.

--
Regards,

Atsushi Torikoshi


Attachments:

  [application/octet-stream] v11-0001-Add-storage-I-O-tracking-to-BUFFERS-option.patch (73.9K, ../../CAM6-o=DnHSj2q9_+Wohrvagd-QAqvpoepNRS9LRadMBCkTAMkw@mail.gmail.com/2-v11-0001-Add-storage-I-O-tracking-to-BUFFERS-option.patch)
  download | inline diff:
From eb3eed4e801d41be2b9bc3c613eb7d47ab79e66a Mon Sep 17 00:00:00 2001
From: Atsushi Torikoshi <[email protected]>
Date: Sat, 23 May 2026 01:04:52 +0900
Subject: [PATCH v11] Add storage I/O tracking to 'BUFFERS' option

The 'BUFFERS' option currently indicates whether a block hit the shared
buffer, but does not distinguish between a cache hit in the OS cache or
a storage I/O operation.
While shared buffers and OS cache offer similar performance, storage
I/O is significantly slower in comparison in general.  By measuring
the numbers of storage I/O read and write, we can better identify if
storage I/O is a bottleneck in performance.

This patch enables to track storage I/O usage by calling getrusage(2)
at both the planning and execution phase start and end points.

A more granular approach as well as current BUFFERS option(tracking at
each plan node) was considered but found to be impractical due to the
high performance cost of frequent getrusage() calls.

Note that no output is shown when io_method=worker, since asynchronous
workers handle I/O for multiple processes, and isolating the EXPLAIN
target's I/O is difficult.

TODO:
I believe this information is mainly useful when used in auto_explain.
I'm going to implement it if this patch is merged.
---
 doc/src/sgml/ref/explain.sgml                 |  27 +
 src/backend/access/brin/brin.c                |   8 +-
 src/backend/access/gin/gininsert.c            |   8 +-
 src/backend/access/nbtree/nbtsort.c           |   8 +-
 src/backend/commands/explain.c                | 125 ++-
 src/backend/commands/prepare.c                |  12 +-
 src/backend/commands/vacuumparallel.c         |   8 +-
 src/backend/executor/execParallel.c           |  35 +-
 src/backend/executor/instrument.c             |  84 +-
 src/include/commands/explain.h                |   1 +
 src/include/executor/execParallel.h           |   3 +
 src/include/executor/instrument.h             |  21 +-
 src/include/port/win32/sys/resource.h         |   2 +
 src/port/win32getrusage.c                     |   4 +
 .../test_misc/t/011_explain_storage_io.pl     |  89 ++
 src/test/regress/expected/explain_1.out       | 869 ++++++++++++++++++
 src/tools/pgindent/typedefs.list              |   1 +
 17 files changed, 1270 insertions(+), 35 deletions(-)
 create mode 100644 src/test/modules/test_misc/t/011_explain_storage_io.pl
 create mode 100644 src/test/regress/expected/explain_1.out

diff --git a/doc/src/sgml/ref/explain.sgml b/doc/src/sgml/ref/explain.sgml
index e95e19081e1..0723bc71318 100644
--- a/doc/src/sgml/ref/explain.sgml
+++ b/doc/src/sgml/ref/explain.sgml
@@ -208,6 +208,33 @@ ROLLBACK;
       <literal>TRUE</literal> without <literal>ANALYZE</literal>,
       only buffer usage during the query planning phase is reported.
      </para>
+     <para>
+      If possible, this option also displays <emphasis>Storage I/O</emphasis>
+      statistics at the end of the plan. The storage I/O
+      <emphasis>read</emphasis> value indicates the number of read operations
+      performed on storage during query planning and execution, while the
+      Storage I/O <emphasis>write</emphasis> value indicates the number of
+      write operations performed on storage during these phases.
+      These values are obtained from the <function>getrusage()</function> system
+      call for the backend process executing the query and for any parallel
+      query worker processes involved in the query.
+      Note that on platforms that do not support
+      <function>getrusage()</function>, such as Windows, no output will be shown,
+      even if reads or writes actually occur. Also, when
+      <xref linkend="guc-io-method"/> is set to <literal>worker</literal>, no output
+      will be shown, as I/O handled by asynchronous workers cannot be measured
+      accurately.
+      The timing and unit of measurement for read and write operations may vary
+      depending on the platform. For example, on Linux, a read is counted only
+      if this process caused data to be fetched from the storage layer, and a
+      write is counted at the page-dirtying time. On Linux, the unit of
+      measurement for read and write operations is 512 bytes.
+     </para>
+     <para>
+      Buffers information is included by default when <literal>ANALYZE</literal>
+      is used but otherwise is not included by default, but can be enabled using
+      this option.
+     </para>
     </listitem>
    </varlistentry>
 
diff --git a/src/backend/access/brin/brin.c b/src/backend/access/brin/brin.c
index bdb30752e09..1173ace160c 100644
--- a/src/backend/access/brin/brin.c
+++ b/src/backend/access/brin/brin.c
@@ -2573,7 +2573,7 @@ _brin_end_parallel(BrinLeader *brinleader, BrinBuildState *state)
 	 * or we might get incomplete data.)
 	 */
 	for (i = 0; i < brinleader->pcxt->nworkers_launched; i++)
-		InstrAccumParallelQuery(&brinleader->bufferusage[i], &brinleader->walusage[i]);
+		InstrAccumParallelQuery(&brinleader->bufferusage[i], NULL, &brinleader->walusage[i]);
 
 	/* Free last reference to MVCC snapshot, if one was used */
 	if (IsMVCCSnapshot(brinleader->snapshot))
@@ -2936,7 +2936,7 @@ _brin_parallel_build_main(dsm_segment *seg, shm_toc *toc)
 	tuplesort_attach_shared(sharedsort, seg);
 
 	/* Prepare to track buffer usage during parallel execution */
-	InstrStartParallelQuery();
+	InstrStartParallelQuery(NULL);
 
 	/*
 	 * Might as well use reliable figure when doling out maintenance_work_mem
@@ -2951,8 +2951,8 @@ _brin_parallel_build_main(dsm_segment *seg, shm_toc *toc)
 	/* Report WAL/buffer usage during parallel execution */
 	bufferusage = shm_toc_lookup(toc, PARALLEL_KEY_BUFFER_USAGE, false);
 	walusage = shm_toc_lookup(toc, PARALLEL_KEY_WAL_USAGE, false);
-	InstrEndParallelQuery(&bufferusage[ParallelWorkerNumber],
-						  &walusage[ParallelWorkerNumber]);
+	InstrEndParallelQuery(&bufferusage[ParallelWorkerNumber], NULL,
+						  &walusage[ParallelWorkerNumber], NULL);
 
 	index_close(indexRel, indexLockmode);
 	table_close(heapRel, heapLockmode);
diff --git a/src/backend/access/gin/gininsert.c b/src/backend/access/gin/gininsert.c
index cb9ed3b563c..f86852c52ef 100644
--- a/src/backend/access/gin/gininsert.c
+++ b/src/backend/access/gin/gininsert.c
@@ -1125,7 +1125,7 @@ _gin_end_parallel(GinLeader *ginleader, GinBuildState *state)
 	 * or we might get incomplete data.)
 	 */
 	for (i = 0; i < ginleader->pcxt->nworkers_launched; i++)
-		InstrAccumParallelQuery(&ginleader->bufferusage[i], &ginleader->walusage[i]);
+		InstrAccumParallelQuery(&ginleader->bufferusage[i], NULL, &ginleader->walusage[i]);
 
 	/* Free last reference to MVCC snapshot, if one was used */
 	if (IsMVCCSnapshot(ginleader->snapshot))
@@ -2186,7 +2186,7 @@ _gin_parallel_build_main(dsm_segment *seg, shm_toc *toc)
 	tuplesort_attach_shared(sharedsort, seg);
 
 	/* Prepare to track buffer usage during parallel execution */
-	InstrStartParallelQuery();
+	InstrStartParallelQuery(NULL);
 
 	/*
 	 * Might as well use reliable figure when doling out maintenance_work_mem
@@ -2201,8 +2201,8 @@ _gin_parallel_build_main(dsm_segment *seg, shm_toc *toc)
 	/* Report WAL/buffer usage during parallel execution */
 	bufferusage = shm_toc_lookup(toc, PARALLEL_KEY_BUFFER_USAGE, false);
 	walusage = shm_toc_lookup(toc, PARALLEL_KEY_WAL_USAGE, false);
-	InstrEndParallelQuery(&bufferusage[ParallelWorkerNumber],
-						  &walusage[ParallelWorkerNumber]);
+	InstrEndParallelQuery(&bufferusage[ParallelWorkerNumber], NULL,
+						  &walusage[ParallelWorkerNumber], NULL);
 
 	index_close(indexRel, indexLockmode);
 	table_close(heapRel, heapLockmode);
diff --git a/src/backend/access/nbtree/nbtsort.c b/src/backend/access/nbtree/nbtsort.c
index 756dfa3dcf4..127be2600a8 100644
--- a/src/backend/access/nbtree/nbtsort.c
+++ b/src/backend/access/nbtree/nbtsort.c
@@ -1620,7 +1620,7 @@ _bt_end_parallel(BTLeader *btleader)
 	 * or we might get incomplete data.)
 	 */
 	for (i = 0; i < btleader->pcxt->nworkers_launched; i++)
-		InstrAccumParallelQuery(&btleader->bufferusage[i], &btleader->walusage[i]);
+		InstrAccumParallelQuery(&btleader->bufferusage[i], NULL, &btleader->walusage[i]);
 
 	/* Free last reference to MVCC snapshot, if one was used */
 	if (IsMVCCSnapshot(btleader->snapshot))
@@ -1828,7 +1828,7 @@ _bt_parallel_build_main(dsm_segment *seg, shm_toc *toc)
 	}
 
 	/* Prepare to track buffer usage during parallel execution */
-	InstrStartParallelQuery();
+	InstrStartParallelQuery(NULL);
 
 	/* Perform sorting of spool, and possibly a spool2 */
 	sortmem = maintenance_work_mem / btshared->scantuplesortstates;
@@ -1838,8 +1838,8 @@ _bt_parallel_build_main(dsm_segment *seg, shm_toc *toc)
 	/* Report WAL/buffer usage during parallel execution */
 	bufferusage = shm_toc_lookup(toc, PARALLEL_KEY_BUFFER_USAGE, false);
 	walusage = shm_toc_lookup(toc, PARALLEL_KEY_WAL_USAGE, false);
-	InstrEndParallelQuery(&bufferusage[ParallelWorkerNumber],
-						  &walusage[ParallelWorkerNumber]);
+	InstrEndParallelQuery(&bufferusage[ParallelWorkerNumber], NULL,
+						  &walusage[ParallelWorkerNumber], NULL);
 
 #ifdef BTREE_BUILD_STATS
 	if (log_btree_build_stats)
diff --git a/src/backend/commands/explain.c b/src/backend/commands/explain.c
index 112c17b0d64..c3fff9a9b18 100644
--- a/src/backend/commands/explain.c
+++ b/src/backend/commands/explain.c
@@ -33,6 +33,7 @@
 #include "parser/analyze.h"
 #include "parser/parsetree.h"
 #include "rewrite/rewriteHandler.h"
+#include "storage/aio_subsys.h"
 #include "storage/bufmgr.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
@@ -148,6 +149,8 @@ static void show_foreignscan_info(ForeignScanState *fsstate, ExplainState *es);
 static const char *explain_get_index_name(Oid indexId);
 static bool peek_buffer_usage(ExplainState *es, const BufferUsage *usage);
 static void show_buffer_usage(ExplainState *es, const BufferUsage *usage);
+static bool peek_storageio_usage(ExplainState *es, const StorageIOUsage *usage);
+static void show_storageio_usage(ExplainState *es, const StorageIOUsage *usage);
 static void show_wal_usage(ExplainState *es, const WalUsage *usage);
 static void show_memory_counters(ExplainState *es,
 								 const MemoryContextCounters *mem_counters);
@@ -331,6 +334,8 @@ standard_ExplainOneQuery(Query *query, int cursorOptions,
 				planduration;
 	BufferUsage bufusage_start,
 				bufusage;
+	StorageIOUsage storageio,
+				storageio_start;
 	MemoryContextCounters mem_counters;
 	MemoryContext planner_ctx = NULL;
 	MemoryContext saved_ctx = NULL;
@@ -352,7 +357,10 @@ standard_ExplainOneQuery(Query *query, int cursorOptions,
 	}
 
 	if (es->buffers)
+	{
 		bufusage_start = pgBufferUsage;
+		GetStorageIOUsage(&storageio_start);
+	}
 	INSTR_TIME_SET_CURRENT(planstart);
 
 	/* plan the query */
@@ -367,16 +375,20 @@ standard_ExplainOneQuery(Query *query, int cursorOptions,
 		MemoryContextMemConsumed(planner_ctx, &mem_counters);
 	}
 
-	/* calc differences of buffer counters. */
+	/* calc differences of buffer and storage I/O counters. */
 	if (es->buffers)
 	{
 		memset(&bufusage, 0, sizeof(BufferUsage));
 		BufferUsageAccumDiff(&bufusage, &pgBufferUsage, &bufusage_start);
+
+		GetStorageIOUsage(&storageio);
+		StorageIOUsageDiff(&storageio, &storageio_start);
 	}
 
 	/* run it (if needed) and produce output */
 	ExplainOnePlan(plan, into, es, queryString, params, queryEnv,
 				   &planduration, (es->buffers ? &bufusage : NULL),
+				   es->buffers ? &storageio : NULL,
 				   es->memory ? &mem_counters : NULL);
 }
 
@@ -500,7 +512,7 @@ void
 ExplainOnePlan(PlannedStmt *plannedstmt, IntoClause *into, ExplainState *es,
 			   const char *queryString, ParamListInfo params,
 			   QueryEnvironment *queryEnv, const instr_time *planduration,
-			   const BufferUsage *bufusage,
+			   const BufferUsage *bufusage, const StorageIOUsage *planstorageio,
 			   const MemoryContextCounters *mem_counters)
 {
 	DestReceiver *dest;
@@ -510,6 +522,7 @@ ExplainOnePlan(PlannedStmt *plannedstmt, IntoClause *into, ExplainState *es,
 	int			eflags;
 	int			instrument_option = 0;
 	SerializeMetrics serializeMetrics = {0};
+	StorageIOUsage storageio_start;
 
 	Assert(plannedstmt->commandType != CMD_UTILITY);
 
@@ -519,7 +532,19 @@ ExplainOnePlan(PlannedStmt *plannedstmt, IntoClause *into, ExplainState *es,
 		instrument_option |= INSTRUMENT_ROWS;
 
 	if (es->buffers)
+	{
+		GetStorageIOUsage(&storageio_start);
+
+		/*
+		 * Initialize global variable counters for parallel query workers.
+		 * Even if the query is cancelled on the way, the EXPLAIN execution
+		 * always passes here, so it can be initialized here.
+		 */
+		pgStorageIOUsageParallel.inblock = 0;
+		pgStorageIOUsageParallel.outblock = 0;
+
 		instrument_option |= INSTRUMENT_BUFFERS;
+	}
 	if (es->wal)
 		instrument_option |= INSTRUMENT_WAL;
 	if (es->io)
@@ -605,8 +630,9 @@ ExplainOnePlan(PlannedStmt *plannedstmt, IntoClause *into, ExplainState *es,
 	/* Create textual dump of plan tree */
 	ExplainPrintPlan(es, queryDesc);
 
-	/* Show buffer and/or memory usage in planning */
-	if (peek_buffer_usage(es, bufusage) || mem_counters)
+	/* Show buffer, storage I/O, and/or memory usage in planning */
+	if (peek_buffer_usage(es, bufusage) || peek_storageio_usage(es, planstorageio) ||
+		mem_counters)
 	{
 		ExplainOpenGroup("Planning", "Planning", true, es);
 
@@ -618,8 +644,10 @@ ExplainOnePlan(PlannedStmt *plannedstmt, IntoClause *into, ExplainState *es,
 		}
 
 		if (bufusage)
+		{
 			show_buffer_usage(es, bufusage);
-
+			show_storageio_usage(es, planstorageio);
+		}
 		if (mem_counters)
 			show_memory_counters(es, mem_counters);
 
@@ -676,6 +704,34 @@ ExplainOnePlan(PlannedStmt *plannedstmt, IntoClause *into, ExplainState *es,
 
 	totaltime += elapsed_time(&starttime);
 
+	/* Show storage I/O usage in execution */
+	if (es->buffers)
+	{
+		StorageIOUsage storageio;
+
+		GetStorageIOUsage(&storageio);
+		StorageIOUsageDiff(&storageio, &storageio_start);
+		StorageIOUsageAdd(&storageio, &pgStorageIOUsageParallel);
+
+		if (peek_storageio_usage(es, &storageio))
+		{
+			ExplainOpenGroup("Execution", "Execution", true, es);
+
+			if (es->format == EXPLAIN_FORMAT_TEXT)
+			{
+				ExplainIndentText(es);
+				appendStringInfoString(es->str, "Execution:\n");
+				es->indent++;
+			}
+			show_storageio_usage(es, &storageio);
+
+			if (es->format == EXPLAIN_FORMAT_TEXT)
+				es->indent--;
+
+			ExplainCloseGroup("Execution", "Execution", true, es);
+		}
+	}
+
 	/*
 	 * We only report execution time if we actually ran the query (that is,
 	 * the user specified ANALYZE), and if summary reporting is enabled (the
@@ -4454,6 +4510,65 @@ show_buffer_usage(ExplainState *es, const BufferUsage *usage)
 	}
 }
 
+/*
+ * Return whether show_storageio_usage would have anything to print, if given
+ * the same 'usage' data.  Note that when the format is anything other than
+ * text, we print even if the counters are all zeroes.
+ */
+static bool
+peek_storageio_usage(ExplainState *es, const StorageIOUsage *usage)
+{
+	if (usage == NULL)
+		return false;
+
+	/*
+	 * Since showing only the I/O excluding AIO workers underestimates the
+	 * total I/O, treat this case as having nothing to print.
+	 */
+	if (pgaio_workers_enabled())
+		return false;
+
+	if (es->format != EXPLAIN_FORMAT_TEXT)
+		return true;
+
+	return usage->inblock > 0 || usage->outblock > 0;
+}
+
+/*
+ * Show storage I/O usage.
+ */
+static void
+show_storageio_usage(ExplainState *es, const StorageIOUsage *usage)
+{
+	/*
+	 * Since showing only the I/O excluding AIO workers underestimates the
+	 * total I/O, do not show anything.
+	 */
+	if (pgaio_workers_enabled())
+		return;
+
+	if (es->format == EXPLAIN_FORMAT_TEXT)
+	{
+		/* Show only positive counter values. */
+		if (usage->inblock <= 0 && usage->outblock <= 0)
+			return;
+
+		ExplainIndentText(es);
+		appendStringInfoString(es->str, "Storage I/O:");
+		appendStringInfo(es->str, " read=%ld", (long) usage->inblock);
+		appendStringInfo(es->str, " write=%ld", (long) usage->outblock);
+
+		appendStringInfoChar(es->str, '\n');
+	}
+	else
+	{
+		ExplainPropertyInteger("Storage I/O Read", NULL,
+							   usage->inblock, es);
+		ExplainPropertyInteger("Storage I/O Write", NULL,
+							   usage->outblock, es);
+	}
+}
+
 /*
  * Show WAL usage details.
  */
diff --git a/src/backend/commands/prepare.c b/src/backend/commands/prepare.c
index 876aad2100a..ae463b9a413 100644
--- a/src/backend/commands/prepare.c
+++ b/src/backend/commands/prepare.c
@@ -584,6 +584,8 @@ ExplainExecuteQuery(ExecuteStmt *execstmt, IntoClause *into, ExplainState *es,
 	instr_time	planduration;
 	BufferUsage bufusage_start,
 				bufusage;
+	StorageIOUsage storageio,
+				storageio_start;
 	MemoryContextCounters mem_counters;
 	MemoryContext planner_ctx = NULL;
 	MemoryContext saved_ctx = NULL;
@@ -599,7 +601,11 @@ ExplainExecuteQuery(ExecuteStmt *execstmt, IntoClause *into, ExplainState *es,
 	}
 
 	if (es->buffers)
+	{
 		bufusage_start = pgBufferUsage;
+		GetStorageIOUsage(&storageio_start);
+	}
+
 	INSTR_TIME_SET_CURRENT(planstart);
 
 	/* Look it up in the hash table */
@@ -644,11 +650,14 @@ ExplainExecuteQuery(ExecuteStmt *execstmt, IntoClause *into, ExplainState *es,
 		MemoryContextMemConsumed(planner_ctx, &mem_counters);
 	}
 
-	/* calc differences of buffer counters. */
+	/* calc differences of buffer and storage I/O counters. */
 	if (es->buffers)
 	{
 		memset(&bufusage, 0, sizeof(BufferUsage));
 		BufferUsageAccumDiff(&bufusage, &pgBufferUsage, &bufusage_start);
+
+		GetStorageIOUsage(&storageio);
+		StorageIOUsageDiff(&storageio, &storageio_start);
 	}
 
 	plan_list = cplan->stmt_list;
@@ -661,6 +670,7 @@ ExplainExecuteQuery(ExecuteStmt *execstmt, IntoClause *into, ExplainState *es,
 		if (pstmt->commandType != CMD_UTILITY)
 			ExplainOnePlan(pstmt, into, es, query_string, paramLI, pstate->p_queryEnv,
 						   &planduration, (es->buffers ? &bufusage : NULL),
+						   es->buffers ? &storageio : NULL,
 						   es->memory ? &mem_counters : NULL);
 		else
 			ExplainOneUtility(pstmt->utilityStmt, into, es, pstate, paramLI);
diff --git a/src/backend/commands/vacuumparallel.c b/src/backend/commands/vacuumparallel.c
index 41cefcfde54..8fadab571f4 100644
--- a/src/backend/commands/vacuumparallel.c
+++ b/src/backend/commands/vacuumparallel.c
@@ -945,7 +945,7 @@ parallel_vacuum_process_all_indexes(ParallelVacuumState *pvs, int num_index_scan
 		WaitForParallelWorkersToFinish(pvs->pcxt);
 
 		for (int i = 0; i < pvs->pcxt->nworkers_launched; i++)
-			InstrAccumParallelQuery(&pvs->buffer_usage[i], &pvs->wal_usage[i]);
+			InstrAccumParallelQuery(&pvs->buffer_usage[i], NULL, &pvs->wal_usage[i]);
 	}
 
 	/*
@@ -1305,7 +1305,7 @@ parallel_vacuum_main(dsm_segment *seg, shm_toc *toc)
 	error_context_stack = &errcallback;
 
 	/* Prepare to track buffer usage during parallel execution */
-	InstrStartParallelQuery();
+	InstrStartParallelQuery(NULL);
 
 	/* Process indexes to perform vacuum/cleanup */
 	parallel_vacuum_process_safe_indexes(&pvs);
@@ -1313,8 +1313,8 @@ parallel_vacuum_main(dsm_segment *seg, shm_toc *toc)
 	/* Report buffer/WAL usage during parallel execution */
 	buffer_usage = shm_toc_lookup(toc, PARALLEL_VACUUM_KEY_BUFFER_USAGE, false);
 	wal_usage = shm_toc_lookup(toc, PARALLEL_VACUUM_KEY_WAL_USAGE, false);
-	InstrEndParallelQuery(&buffer_usage[ParallelWorkerNumber],
-						  &wal_usage[ParallelWorkerNumber]);
+	InstrEndParallelQuery(&buffer_usage[ParallelWorkerNumber], NULL,
+						  &wal_usage[ParallelWorkerNumber], NULL);
 
 	/* Report any remaining cost-based vacuum delay time */
 	if (track_cost_delay_timing)
diff --git a/src/backend/executor/execParallel.c b/src/backend/executor/execParallel.c
index 81b87d82fab..44183f303b8 100644
--- a/src/backend/executor/execParallel.c
+++ b/src/backend/executor/execParallel.c
@@ -67,6 +67,7 @@
 #define PARALLEL_KEY_QUERY_TEXT		UINT64CONST(0xE000000000000008)
 #define PARALLEL_KEY_JIT_INSTRUMENTATION UINT64CONST(0xE000000000000009)
 #define PARALLEL_KEY_WAL_USAGE			UINT64CONST(0xE00000000000000A)
+#define PARALLEL_KEY_STORAGEIO_USAGE	UINT64CONST(0xE00000000000000B)
 
 #define PARALLEL_TUPLE_QUEUE_SIZE		65536
 
@@ -663,6 +664,7 @@ ExecInitParallelPlan(PlanState *planstate, EState *estate,
 	char	   *pstmt_space;
 	char	   *paramlistinfo_space;
 	BufferUsage *bufusage_space;
+	StorageIOUsage *storageiousage_space;
 	WalUsage   *walusage_space;
 	SharedExecutorInstrumentation *instrumentation = NULL;
 	SharedJitInstrumentation *jit_instrumentation = NULL;
@@ -744,6 +746,13 @@ ExecInitParallelPlan(PlanState *planstate, EState *estate,
 						   mul_size(sizeof(WalUsage), pcxt->nworkers));
 	shm_toc_estimate_keys(&pcxt->estimator, 1);
 
+	/*
+	 * Same thing for StorageIOUsage.
+	 */
+	shm_toc_estimate_chunk(&pcxt->estimator,
+						   mul_size(sizeof(StorageIOUsage), pcxt->nworkers));
+	shm_toc_estimate_keys(&pcxt->estimator, 1);
+
 	/* Estimate space for tuple queues. */
 	shm_toc_estimate_chunk(&pcxt->estimator,
 						   mul_size(PARALLEL_TUPLE_QUEUE_SIZE, pcxt->nworkers));
@@ -839,6 +848,12 @@ ExecInitParallelPlan(PlanState *planstate, EState *estate,
 	shm_toc_insert(pcxt->toc, PARALLEL_KEY_WAL_USAGE, walusage_space);
 	pei->wal_usage = walusage_space;
 
+	/* Same for StorageIOUsage. */
+	storageiousage_space = shm_toc_allocate(pcxt->toc,
+											mul_size(sizeof(StorageIOUsage), pcxt->nworkers));
+	shm_toc_insert(pcxt->toc, PARALLEL_KEY_STORAGEIO_USAGE, storageiousage_space);
+	pei->storageio_usage = storageiousage_space;
+
 	/* Set up the tuple queues that the workers will write into. */
 	pei->tqueue = ExecParallelSetupTupleQueues(pcxt, false);
 
@@ -1255,11 +1270,11 @@ ExecParallelFinish(ParallelExecutorInfo *pei)
 	WaitForParallelWorkersToFinish(pei->pcxt);
 
 	/*
-	 * Next, accumulate buffer/WAL usage.  (This must wait for the workers to
-	 * finish, or we might get incomplete data.)
+	 * Next, accumulate buffer, WAL, and Storage I/O usage. (This must wait
+	 * for the workers to finish, or we might get incomplete data.)
 	 */
 	for (i = 0; i < nworkers; i++)
-		InstrAccumParallelQuery(&pei->buffer_usage[i], &pei->wal_usage[i]);
+		InstrAccumParallelQuery(&pei->buffer_usage[i], &pei->storageio_usage[i], &pei->wal_usage[i]);
 
 	pei->finished = true;
 }
@@ -1515,6 +1530,8 @@ ParallelQueryMain(dsm_segment *seg, shm_toc *toc)
 {
 	FixedParallelExecutorState *fpes;
 	BufferUsage *buffer_usage;
+	StorageIOUsage *storageio_usage;
+	StorageIOUsage storageio_usage_start;
 	WalUsage   *wal_usage;
 	DestReceiver *receiver;
 	QueryDesc  *queryDesc;
@@ -1568,13 +1585,14 @@ ParallelQueryMain(dsm_segment *seg, shm_toc *toc)
 	ExecSetTupleBound(fpes->tuples_needed, queryDesc->planstate);
 
 	/*
-	 * Prepare to track buffer/WAL usage during query execution.
+	 * Prepare to track buffer, WAL, and StorageI/O usage during query
+	 * execution.
 	 *
 	 * We do this after starting up the executor to match what happens in the
 	 * leader, which also doesn't count buffer accesses and WAL activity that
 	 * occur during executor startup.
 	 */
-	InstrStartParallelQuery();
+	InstrStartParallelQuery(&storageio_usage_start);
 
 	/*
 	 * Run the plan.  If we specified a tuple bound, be careful not to demand
@@ -1587,11 +1605,14 @@ ParallelQueryMain(dsm_segment *seg, shm_toc *toc)
 	/* Shut down the executor */
 	ExecutorFinish(queryDesc);
 
-	/* Report buffer/WAL usage during parallel execution. */
+	/* Report buffer, WAL, and storage I/O usage during parallel execution. */
 	buffer_usage = shm_toc_lookup(toc, PARALLEL_KEY_BUFFER_USAGE, false);
+	storageio_usage = shm_toc_lookup(toc, PARALLEL_KEY_STORAGEIO_USAGE, false);
 	wal_usage = shm_toc_lookup(toc, PARALLEL_KEY_WAL_USAGE, false);
 	InstrEndParallelQuery(&buffer_usage[ParallelWorkerNumber],
-						  &wal_usage[ParallelWorkerNumber]);
+						  &storageio_usage[ParallelWorkerNumber],
+						  &wal_usage[ParallelWorkerNumber],
+						  &storageio_usage_start);
 
 	/* Report instrumentation data if any instrumentation options are set. */
 	if (instrumentation != NULL)
diff --git a/src/backend/executor/instrument.c b/src/backend/executor/instrument.c
index ffbcd572133..d84769b0210 100644
--- a/src/backend/executor/instrument.c
+++ b/src/backend/executor/instrument.c
@@ -13,6 +13,7 @@
  */
 #include "postgres.h"
 
+#include <sys/resource.h>
 #include <unistd.h>
 
 #include "executor/executor.h"
@@ -20,14 +21,24 @@
 #include "executor/tuptable.h"
 #include "nodes/execnodes.h"
 #include "portability/instr_time.h"
+#include "storage/aio_subsys.h"
 #include "utils/guc_hooks.h"
 
 BufferUsage pgBufferUsage;
 static BufferUsage save_pgBufferUsage;
+
+/*
+ * Accumulates the I/O usage sent by parallel workers to the main
+ * process. This does not contain the I/O from the main backend process
+ * itself because the kernel tracks that instead of us.
+ */
+StorageIOUsage pgStorageIOUsageParallel;
+
 WalUsage	pgWalUsage;
 static WalUsage save_pgWalUsage;
 
 static void BufferUsageAdd(BufferUsage *dst, const BufferUsage *add);
+void		StorageIOUsageAdd(StorageIOUsage *dst, const StorageIOUsage *add);
 static void WalUsageAdd(WalUsage *dst, WalUsage *add);
 
 
@@ -276,27 +287,43 @@ InstrStopTrigger(TriggerInstrumentation *tginstr, int64 firings)
 
 /* note current values during parallel executor startup */
 void
-InstrStartParallelQuery(void)
+InstrStartParallelQuery(StorageIOUsage *storageiousage)
 {
 	save_pgBufferUsage = pgBufferUsage;
 	save_pgWalUsage = pgWalUsage;
+
+	if (storageiousage != NULL)
+		GetStorageIOUsage(storageiousage);
 }
 
 /* report usage after parallel executor shutdown */
 void
-InstrEndParallelQuery(BufferUsage *bufusage, WalUsage *walusage)
+InstrEndParallelQuery(BufferUsage *bufusage, StorageIOUsage *storageiousage, WalUsage *walusage, StorageIOUsage *storageiousage_start)
 {
 	memset(bufusage, 0, sizeof(BufferUsage));
 	BufferUsageAccumDiff(bufusage, &pgBufferUsage, &save_pgBufferUsage);
+
+	if (storageiousage != NULL && storageiousage_start != NULL)
+	{
+		struct StorageIOUsage storageiousage_end;
+
+		GetStorageIOUsage(&storageiousage_end);
+
+		memset(storageiousage, 0, sizeof(StorageIOUsage));
+		StorageIOUsageAccumDiff(storageiousage, &storageiousage_end, storageiousage_start);
+	}
 	memset(walusage, 0, sizeof(WalUsage));
 	WalUsageAccumDiff(walusage, &pgWalUsage, &save_pgWalUsage);
 }
 
 /* accumulate work done by workers in leader's stats */
 void
-InstrAccumParallelQuery(BufferUsage *bufusage, WalUsage *walusage)
+InstrAccumParallelQuery(BufferUsage *bufusage, StorageIOUsage *storageiousage, WalUsage *walusage)
 {
 	BufferUsageAdd(&pgBufferUsage, bufusage);
+
+	if (storageiousage != NULL)
+		StorageIOUsageAdd(&pgStorageIOUsageParallel, storageiousage);
 	WalUsageAdd(&pgWalUsage, walusage);
 }
 
@@ -352,6 +379,57 @@ BufferUsageAccumDiff(BufferUsage *dst,
 						  add->temp_blk_write_time, sub->temp_blk_write_time);
 }
 
+/* helper functions for StorageIOUsage usage accumulation */
+void
+StorageIOUsageAdd(StorageIOUsage *dst, const StorageIOUsage *add)
+{
+	dst->inblock += add->inblock;
+	dst->outblock += add->outblock;
+}
+
+/* dst += add - sub */
+void
+StorageIOUsageAccumDiff(StorageIOUsage *dst, const StorageIOUsage *add, const StorageIOUsage *sub)
+{
+	dst->inblock += add->inblock - sub->inblock;
+	dst->outblock += add->outblock - sub->outblock;
+}
+
+/* dst -= sub */
+void
+StorageIOUsageDiff(StorageIOUsage *dst, const StorageIOUsage *sub)
+{
+	dst->inblock -= sub->inblock;
+	dst->outblock -= sub->outblock;
+}
+
+/* Captures the current storage I/O usage statistics */
+void
+GetStorageIOUsage(StorageIOUsage *usage)
+{
+	struct rusage rusage;
+
+	/*
+	 * Since getting the I/O excluding AIO workers underestimates the total
+	 * I/O, don't get the I/O usage statistics when AIO worker is enabled.
+	 */
+	if (pgaio_workers_enabled())
+	{
+		usage->inblock = 0;
+		usage->outblock = 0;
+		return;
+	}
+
+	if (getrusage(RUSAGE_SELF, &rusage))
+	{
+		ereport(ERROR,
+				(errcode(ERRCODE_SYSTEM_ERROR),
+				 errmsg("getrusage() failed: %m")));
+	}
+	usage->inblock = rusage.ru_inblock;
+	usage->outblock = rusage.ru_oublock;
+}
+
 /* helper functions for WAL usage accumulation */
 static inline void
 WalUsageAdd(WalUsage *dst, WalUsage *add)
diff --git a/src/include/commands/explain.h b/src/include/commands/explain.h
index 472e141bba3..bbadc5b0c83 100644
--- a/src/include/commands/explain.h
+++ b/src/include/commands/explain.h
@@ -69,6 +69,7 @@ extern void ExplainOnePlan(PlannedStmt *plannedstmt, IntoClause *into,
 						   ParamListInfo params, QueryEnvironment *queryEnv,
 						   const instr_time *planduration,
 						   const BufferUsage *bufusage,
+						   const StorageIOUsage *planstorageio,
 						   const MemoryContextCounters *mem_counters);
 
 extern void ExplainPrintPlan(ExplainState *es, QueryDesc *queryDesc);
diff --git a/src/include/executor/execParallel.h b/src/include/executor/execParallel.h
index 5a2034811d5..8614d8a5be1 100644
--- a/src/include/executor/execParallel.h
+++ b/src/include/executor/execParallel.h
@@ -14,6 +14,7 @@
 #define EXECPARALLEL_H
 
 #include "access/parallel.h"
+#include "executor/instrument.h"
 #include "nodes/execnodes.h"
 #include "nodes/parsenodes.h"
 #include "nodes/plannodes.h"
@@ -26,6 +27,8 @@ typedef struct ParallelExecutorInfo
 	PlanState  *planstate;		/* plan subtree we're running in parallel */
 	ParallelContext *pcxt;		/* parallel context we're using */
 	BufferUsage *buffer_usage;	/* points to bufusage area in DSM */
+	StorageIOUsage *storageio_usage;	/* points to storageio usage area in
+										 * DSM */
 	WalUsage   *wal_usage;		/* walusage area in DSM */
 	SharedExecutorInstrumentation *instrumentation; /* optional */
 	struct SharedJitInstrumentation *jit_instrumentation;	/* optional */
diff --git a/src/include/executor/instrument.h b/src/include/executor/instrument.h
index f093a52aae0..221926379de 100644
--- a/src/include/executor/instrument.h
+++ b/src/include/executor/instrument.h
@@ -41,6 +41,14 @@ typedef struct BufferUsage
 	instr_time	temp_blk_write_time;	/* time spent writing temp blocks */
 } BufferUsage;
 
+typedef struct StorageIOUsage
+{
+	long		inblock;		/* # of times the file system had to perform
+								 * input */
+	long		outblock;		/* # of times the file system had to perform
+								 * output */
+} StorageIOUsage;
+
 /*
  * WalUsage tracks only WAL activity like WAL records generation that
  * can be measured per query and is displayed by EXPLAIN command,
@@ -126,12 +134,14 @@ typedef struct TriggerInstrumentation
 } TriggerInstrumentation;
 
 extern PGDLLIMPORT BufferUsage pgBufferUsage;
+extern PGDLLIMPORT StorageIOUsage pgStorageIOUsageParallel;
 extern PGDLLIMPORT WalUsage pgWalUsage;
 
 extern Instrumentation *InstrAlloc(int instrument_options);
 extern void InstrInitOptions(Instrumentation *instr, int instrument_options);
 extern void InstrStart(Instrumentation *instr);
 extern void InstrStop(Instrumentation *instr);
+extern void InstrInit(Instrumentation *instr, int instrument_options);
 
 extern NodeInstrumentation *InstrAllocNode(int instrument_options,
 										   bool async_mode);
@@ -147,11 +157,16 @@ extern TriggerInstrumentation *InstrAllocTrigger(int n, int instrument_options);
 extern void InstrStartTrigger(TriggerInstrumentation *tginstr);
 extern void InstrStopTrigger(TriggerInstrumentation *tginstr, int64 firings);
 
-extern void InstrStartParallelQuery(void);
-extern void InstrEndParallelQuery(BufferUsage *bufusage, WalUsage *walusage);
-extern void InstrAccumParallelQuery(BufferUsage *bufusage, WalUsage *walusage);
+extern void InstrStartParallelQuery(StorageIOUsage *storageiousage);
+extern void InstrEndParallelQuery(BufferUsage *bufusage, StorageIOUsage *storageiousage, WalUsage *walusage, StorageIOUsage *storageiousage_start);
+extern void InstrAccumParallelQuery(BufferUsage *bufusage, StorageIOUsage *storageiousage, WalUsage *walusage);
 extern void BufferUsageAccumDiff(BufferUsage *dst,
 								 const BufferUsage *add, const BufferUsage *sub);
+extern void StorageIOUsageAccumDiff(StorageIOUsage *dst,
+									const StorageIOUsage *add, const StorageIOUsage *sub);
+extern void StorageIOUsageDiff(StorageIOUsage *dst, const StorageIOUsage *sub);
+extern void StorageIOUsageAdd(StorageIOUsage *dst, const StorageIOUsage *add);
+extern void GetStorageIOUsage(StorageIOUsage *usage);
 extern void WalUsageAccumDiff(WalUsage *dst, const WalUsage *add,
 							  const WalUsage *sub);
 
diff --git a/src/include/port/win32/sys/resource.h b/src/include/port/win32/sys/resource.h
index a14feeb5844..270dc37c84f 100644
--- a/src/include/port/win32/sys/resource.h
+++ b/src/include/port/win32/sys/resource.h
@@ -13,6 +13,8 @@ struct rusage
 {
 	struct timeval ru_utime;	/* user time used */
 	struct timeval ru_stime;	/* system time used */
+	long		ru_inblock;		/* Currently always 0 for Windows */
+	long		ru_oublock;		/* Currently always 0 for Windows */
 };
 
 extern int	getrusage(int who, struct rusage *rusage);
diff --git a/src/port/win32getrusage.c b/src/port/win32getrusage.c
index fa2b79cd5ed..2e267de7b28 100644
--- a/src/port/win32getrusage.c
+++ b/src/port/win32getrusage.c
@@ -57,5 +57,9 @@ getrusage(int who, struct rusage *rusage)
 	rusage->ru_utime.tv_sec = li.QuadPart / 1000000L;
 	rusage->ru_utime.tv_usec = li.QuadPart % 1000000L;
 
+	/* Currently always 0 for Windows */
+	rusage->ru_inblock = 0;
+	rusage->ru_oublock = 0;
+
 	return 0;
 }
diff --git a/src/test/modules/test_misc/t/011_explain_storage_io.pl b/src/test/modules/test_misc/t/011_explain_storage_io.pl
new file mode 100644
index 00000000000..cb846aee92f
--- /dev/null
+++ b/src/test/modules/test_misc/t/011_explain_storage_io.pl
@@ -0,0 +1,89 @@
+
+# Copyright (c) 2024-2026, PostgreSQL Global Development Group
+
+use strict;
+use warnings FATAL => 'all';
+use locale;
+
+use PostgreSQL::Test::Cluster;
+use PostgreSQL::Test::Utils;
+use Test::More;
+
+# Node initialization
+my $node_sync = PostgreSQL::Test::Cluster->new('sync');
+$node_sync->init();
+$node_sync->append_conf('postgresql.conf', "io_method = sync");
+$node_sync->start;
+
+# Check that the XML-formatted EXPLAIN output contains Storage I/O
+# read and write information.
+my $xml_sync = $node_sync->safe_psql(
+	'postgres',
+	q{
+	EXPLAIN (ANALYZE, BUFFERS, FORMAT XML)
+	SELECT * FROM pg_class;
+	}
+);
+
+like(
+	$xml_sync,
+	qr/<Storage-I-O-Read>\d+<\/Storage-I-O-Read>/,
+	"Storage-I-O-Read is shown in EXPLAIN XML (io_method=sync)"
+);
+
+like(
+	$xml_sync,
+	qr/<Storage-I-O-Write>\d+<\/Storage-I-O-Write>/,
+	"Storage-I-O-Write is shown in EXPLAIN XML (io_method=sync)"
+);
+
+# Do the same test if io_method=io_uring is supported
+if (have_io_uring())
+{
+	my $node_io_uring = PostgreSQL::Test::Cluster->new('io_uring');
+	$node_io_uring->init;
+	$node_io_uring->append_conf('postgresql.conf', "io_method = 'io_uring'");
+	$node_io_uring->start;
+	
+	my $xml_io_uring = $node_io_uring->safe_psql(
+		'postgres',
+		q{
+		EXPLAIN (ANALYZE, BUFFERS, FORMAT XML)
+		SELECT * FROM pg_class;
+		}
+	);
+	
+	like(
+		$xml_io_uring,
+		qr/<Storage-I-O-Read>\d+<\/Storage-I-O-Read>/,
+		"Storage-I-O-Read is shown in EXPLAIN XML (io_method=io_uring)"
+	);
+	
+	like(
+		$xml_io_uring,
+		qr/<Storage-I-O-Write>\d+<\/Storage-I-O-Write>/,
+		"Storage-I-O-Write is shown in EXPLAIN XML (io_method=io_uring)"
+	);
+}
+else
+{
+    note "io_uring is not supported on this platform. skipping io_uring tests";
+}
+
+sub have_io_uring
+{
+        # To detect if io_uring is supported, we look at the error message for
+        # assigning an invalid value to an enum GUC, which lists all the valid
+        # options. We need to use -C to deal with running as administrator on
+        # windows, the superuser check is omitted if -C is used.
+        my ($stdout, $stderr) =
+          run_command [qw(postgres -C invalid -c io_method=invalid)];
+        die "can't determine supported io_method values"
+          unless $stderr =~ m/Available values: ([^\.]+)\./;
+        my $methods = $1;
+        note "supported io_method values are: $methods";
+
+        return ($methods =~ m/io_uring/) ? 1 : 0;
+}
+
+done_testing();
diff --git a/src/test/regress/expected/explain_1.out b/src/test/regress/expected/explain_1.out
new file mode 100644
index 00000000000..54233fd2475
--- /dev/null
+++ b/src/test/regress/expected/explain_1.out
@@ -0,0 +1,869 @@
+--
+-- EXPLAIN
+--
+-- There are many test cases elsewhere that use EXPLAIN as a vehicle for
+-- checking something else (usually planner behavior).  This file is
+-- concerned with testing EXPLAIN in its own right.
+--
+-- To produce stable regression test output, it's usually necessary to
+-- ignore details such as exact costs or row counts.  These filter
+-- functions replace changeable output details with fixed strings.
+create function explain_filter(text) returns setof text
+language plpgsql as
+$$
+declare
+    ln text;
+begin
+    for ln in execute $1
+    loop
+        -- Replace any numeric word with just 'N'
+        ln := regexp_replace(ln, '-?\m\d+\M', 'N', 'g');
+        -- In sort output, the above won't match units-suffixed numbers
+        ln := regexp_replace(ln, '\m\d+kB', 'NkB', 'g');
+        -- Ignore text-mode buffers output because it varies depending
+        -- on the system state
+        CONTINUE WHEN (ln ~ ' +Buffers: .*');
+        -- Ignore text-mode "Planning:" line because whether it's output
+        -- varies depending on the system state
+        CONTINUE WHEN (ln = 'Planning:');
+        return next ln;
+    end loop;
+end;
+$$;
+-- To produce valid JSON output, replace numbers with "0" or "0.0" not "N"
+create function explain_filter_to_json(text) returns jsonb
+language plpgsql as
+$$
+declare
+    data text := '';
+    ln text;
+begin
+    for ln in execute $1
+    loop
+        -- Replace any numeric word with just '0'
+        ln := regexp_replace(ln, '\m\d+\M', '0', 'g');
+        data := data || ln;
+    end loop;
+    return data::jsonb;
+end;
+$$;
+-- Disable JIT, or we'll get different output on machines where that's been
+-- forced on
+set jit = off;
+-- Similarly, disable track_io_timing, to avoid output differences when
+-- enabled.
+set track_io_timing = off;
+-- Simple cases
+explain (costs off) select 1 as a, 2 as b having false;
+        QUERY PLAN        
+--------------------------
+ Result
+   Replaces: Aggregate
+   One-Time Filter: false
+(3 rows)
+
+select explain_filter('explain select * from int8_tbl i8');
+                     explain_filter                      
+---------------------------------------------------------
+ Seq Scan on int8_tbl i8  (cost=N.N..N.N rows=N width=N)
+(1 row)
+
+select explain_filter('explain (analyze, buffers off) select * from int8_tbl i8');
+                                         explain_filter                                          
+-------------------------------------------------------------------------------------------------
+ Seq Scan on int8_tbl i8  (cost=N.N..N.N rows=N width=N) (actual time=N.N..N.N rows=N.N loops=N)
+ Planning Time: N.N ms
+ Execution Time: N.N ms
+(3 rows)
+
+select explain_filter('explain (analyze, buffers off, verbose) select * from int8_tbl i8');
+                                             explain_filter                                             
+--------------------------------------------------------------------------------------------------------
+ Seq Scan on public.int8_tbl i8  (cost=N.N..N.N rows=N width=N) (actual time=N.N..N.N rows=N.N loops=N)
+   Output: q1, q2
+ Planning Time: N.N ms
+ Execution Time: N.N ms
+(4 rows)
+
+select explain_filter('explain (analyze, buffers, format text) select * from int8_tbl i8');
+                                         explain_filter                                          
+-------------------------------------------------------------------------------------------------
+ Seq Scan on int8_tbl i8  (cost=N.N..N.N rows=N width=N) (actual time=N.N..N.N rows=N.N loops=N)
+ Planning Time: N.N ms
+ Execution Time: N.N ms
+(3 rows)
+
+select explain_filter('explain (buffers, format text) select * from int8_tbl i8');
+                     explain_filter                      
+---------------------------------------------------------
+ Seq Scan on int8_tbl i8  (cost=N.N..N.N rows=N width=N)
+(1 row)
+
+\a
+select explain_filter('explain (analyze, buffers, io, format xml) select * from int8_tbl i8');
+explain_filter
+<explain xmlns="http://www.postgresql.org/N/explain">
+  <Query>
+    <Plan>
+      <Node-Type>Seq Scan</Node-Type>
+      <Parallel-Aware>false</Parallel-Aware>
+      <Async-Capable>false</Async-Capable>
+      <Relation-Name>int8_tbl</Relation-Name>
+      <Alias>i8</Alias>
+      <Startup-Cost>N.N</Startup-Cost>
+      <Total-Cost>N.N</Total-Cost>
+      <Plan-Rows>N</Plan-Rows>
+      <Plan-Width>N</Plan-Width>
+      <Actual-Startup-Time>N.N</Actual-Startup-Time>
+      <Actual-Total-Time>N.N</Actual-Total-Time>
+      <Actual-Rows>N.N</Actual-Rows>
+      <Actual-Loops>N</Actual-Loops>
+      <Disabled>false</Disabled>
+      <Average-Prefetch-Distance>N.N</Average-Prefetch-Distance>
+      <Max-Prefetch-Distance>N</Max-Prefetch-Distance>
+      <Prefetch-Capacity>N</Prefetch-Capacity>
+      <I-O-Count>N</I-O-Count>
+      <I-O-Waits>N</I-O-Waits>
+      <Average-I-O-Size>N.N</Average-I-O-Size>
+      <Average-I-Os-In-Progress>N.N</Average-I-Os-In-Progress>
+      <Shared-Hit-Blocks>N</Shared-Hit-Blocks>
+      <Shared-Read-Blocks>N</Shared-Read-Blocks>
+      <Shared-Dirtied-Blocks>N</Shared-Dirtied-Blocks>
+      <Shared-Written-Blocks>N</Shared-Written-Blocks>
+      <Local-Hit-Blocks>N</Local-Hit-Blocks>
+      <Local-Read-Blocks>N</Local-Read-Blocks>
+      <Local-Dirtied-Blocks>N</Local-Dirtied-Blocks>
+      <Local-Written-Blocks>N</Local-Written-Blocks>
+      <Temp-Read-Blocks>N</Temp-Read-Blocks>
+      <Temp-Written-Blocks>N</Temp-Written-Blocks>
+    </Plan>
+    <Planning>
+      <Shared-Hit-Blocks>N</Shared-Hit-Blocks>
+      <Shared-Read-Blocks>N</Shared-Read-Blocks>
+      <Shared-Dirtied-Blocks>N</Shared-Dirtied-Blocks>
+      <Shared-Written-Blocks>N</Shared-Written-Blocks>
+      <Local-Hit-Blocks>N</Local-Hit-Blocks>
+      <Local-Read-Blocks>N</Local-Read-Blocks>
+      <Local-Dirtied-Blocks>N</Local-Dirtied-Blocks>
+      <Local-Written-Blocks>N</Local-Written-Blocks>
+      <Temp-Read-Blocks>N</Temp-Read-Blocks>
+      <Temp-Written-Blocks>N</Temp-Written-Blocks>
+      <Storage-I-O-Read>N</Storage-I-O-Read>
+      <Storage-I-O-Write>N</Storage-I-O-Write>
+    </Planning>
+    <Planning-Time>N.N</Planning-Time>
+    <Triggers>
+    </Triggers>
+    <Execution>
+      <Storage-I-O-Read>N</Storage-I-O-Read>
+      <Storage-I-O-Write>N</Storage-I-O-Write>
+    </Execution>
+    <Execution-Time>N.N</Execution-Time>
+  </Query>
+</explain>
+(1 row)
+select explain_filter('explain (analyze, serialize, buffers, io, format yaml) select * from int8_tbl i8');
+explain_filter
+- Plan: 
+    Node Type: "Seq Scan"
+    Parallel Aware: false
+    Async Capable: false
+    Relation Name: "int8_tbl"
+    Alias: "i8"
+    Startup Cost: N.N
+    Total Cost: N.N
+    Plan Rows: N
+    Plan Width: N
+    Actual Startup Time: N.N
+    Actual Total Time: N.N
+    Actual Rows: N.N
+    Actual Loops: N
+    Disabled: false
+    Average Prefetch Distance: N.N
+    Max Prefetch Distance: N
+    Prefetch Capacity: N
+    I/O Count: N
+    I/O Waits: N
+    Average I/O Size: N.N
+    Average I/Os In Progress: N.N
+    Shared Hit Blocks: N
+    Shared Read Blocks: N
+    Shared Dirtied Blocks: N
+    Shared Written Blocks: N
+    Local Hit Blocks: N
+    Local Read Blocks: N
+    Local Dirtied Blocks: N
+    Local Written Blocks: N
+    Temp Read Blocks: N
+    Temp Written Blocks: N
+  Planning: 
+    Shared Hit Blocks: N
+    Shared Read Blocks: N
+    Shared Dirtied Blocks: N
+    Shared Written Blocks: N
+    Local Hit Blocks: N
+    Local Read Blocks: N
+    Local Dirtied Blocks: N
+    Local Written Blocks: N
+    Temp Read Blocks: N
+    Temp Written Blocks: N
+    Storage I/O Read: N
+    Storage I/O Write: N
+  Planning Time: N.N
+  Triggers: 
+  Serialization: 
+    Time: N.N
+    Output Volume: N
+    Format: "text"
+    Shared Hit Blocks: N
+    Shared Read Blocks: N
+    Shared Dirtied Blocks: N
+    Shared Written Blocks: N
+    Local Hit Blocks: N
+    Local Read Blocks: N
+    Local Dirtied Blocks: N
+    Local Written Blocks: N
+    Temp Read Blocks: N
+    Temp Written Blocks: N
+  Execution: 
+    Storage I/O Read: N
+    Storage I/O Write: N
+  Execution Time: N.N
+(1 row)
+select explain_filter('explain (buffers, format json) select * from int8_tbl i8');
+explain_filter
+[
+  {
+    "Plan": {
+      "Node Type": "Seq Scan",
+      "Parallel Aware": false,
+      "Async Capable": false,
+      "Relation Name": "int8_tbl",
+      "Alias": "i8",
+      "Startup Cost": N.N,
+      "Total Cost": N.N,
+      "Plan Rows": N,
+      "Plan Width": N,
+      "Disabled": false,
+      "Shared Hit Blocks": N,
+      "Shared Read Blocks": N,
+      "Shared Dirtied Blocks": N,
+      "Shared Written Blocks": N,
+      "Local Hit Blocks": N,
+      "Local Read Blocks": N,
+      "Local Dirtied Blocks": N,
+      "Local Written Blocks": N,
+      "Temp Read Blocks": N,
+      "Temp Written Blocks": N
+    },
+    "Planning": {
+      "Shared Hit Blocks": N,
+      "Shared Read Blocks": N,
+      "Shared Dirtied Blocks": N,
+      "Shared Written Blocks": N,
+      "Local Hit Blocks": N,
+      "Local Read Blocks": N,
+      "Local Dirtied Blocks": N,
+      "Local Written Blocks": N,
+      "Temp Read Blocks": N,
+      "Temp Written Blocks": N,
+      "Storage I/O Read": N,
+      "Storage I/O Write": N
+    },
+    "Execution": {
+      "Storage I/O Read": N,
+      "Storage I/O Write": N
+    }
+  }
+]
+(1 row)
+\a
+-- Check expansion of window definitions
+select explain_filter('explain verbose select sum(unique1) over w, sum(unique2) over (w order by hundred), sum(tenthous) over (w order by hundred) from tenk1 window w as (partition by ten)');
+                                            explain_filter                                             
+-------------------------------------------------------------------------------------------------------
+ WindowAgg  (cost=N.N..N.N rows=N width=N)
+   Output: sum(unique1) OVER w, (sum(unique2) OVER w1), (sum(tenthous) OVER w1), ten, hundred
+   Window: w AS (PARTITION BY tenk1.ten)
+   ->  WindowAgg  (cost=N.N..N.N rows=N width=N)
+         Output: ten, hundred, unique1, unique2, tenthous, sum(unique2) OVER w1, sum(tenthous) OVER w1
+         Window: w1 AS (PARTITION BY tenk1.ten ORDER BY tenk1.hundred)
+         ->  Sort  (cost=N.N..N.N rows=N width=N)
+               Output: ten, hundred, unique1, unique2, tenthous
+               Sort Key: tenk1.ten, tenk1.hundred
+               ->  Seq Scan on public.tenk1  (cost=N.N..N.N rows=N width=N)
+                     Output: ten, hundred, unique1, unique2, tenthous
+(11 rows)
+
+select explain_filter('explain verbose select sum(unique1) over w1, sum(unique2) over (w1 order by hundred), sum(tenthous) over (w1 order by hundred rows 10 preceding) from tenk1 window w1 as (partition by ten)');
+                                             explain_filter                                              
+---------------------------------------------------------------------------------------------------------
+ WindowAgg  (cost=N.N..N.N rows=N width=N)
+   Output: sum(unique1) OVER w1, (sum(unique2) OVER w2), (sum(tenthous) OVER w3), ten, hundred
+   Window: w1 AS (PARTITION BY tenk1.ten)
+   ->  WindowAgg  (cost=N.N..N.N rows=N width=N)
+         Output: ten, hundred, unique1, unique2, tenthous, (sum(unique2) OVER w2), sum(tenthous) OVER w3
+         Window: w3 AS (PARTITION BY tenk1.ten ORDER BY tenk1.hundred ROWS 'N'::bigint PRECEDING)
+         ->  WindowAgg  (cost=N.N..N.N rows=N width=N)
+               Output: ten, hundred, unique1, unique2, tenthous, sum(unique2) OVER w2
+               Window: w2 AS (PARTITION BY tenk1.ten ORDER BY tenk1.hundred)
+               ->  Sort  (cost=N.N..N.N rows=N width=N)
+                     Output: ten, hundred, unique1, unique2, tenthous
+                     Sort Key: tenk1.ten, tenk1.hundred
+                     ->  Seq Scan on public.tenk1  (cost=N.N..N.N rows=N width=N)
+                           Output: ten, hundred, unique1, unique2, tenthous
+(14 rows)
+
+-- Check output including I/O timings.  These fields are conditional
+-- but always set in JSON format, so check them only in this case.
+set track_io_timing = on;
+select explain_filter('explain (analyze, buffers, format json) select * from int8_tbl i8');
+           explain_filter            
+-------------------------------------
+ [                                  +
+   {                                +
+     "Plan": {                      +
+       "Node Type": "Seq Scan",     +
+       "Parallel Aware": false,     +
+       "Async Capable": false,      +
+       "Relation Name": "int8_tbl", +
+       "Alias": "i8",               +
+       "Startup Cost": N.N,         +
+       "Total Cost": N.N,           +
+       "Plan Rows": N,              +
+       "Plan Width": N,             +
+       "Actual Startup Time": N.N,  +
+       "Actual Total Time": N.N,    +
+       "Actual Rows": N.N,          +
+       "Actual Loops": N,           +
+       "Disabled": false,           +
+       "Shared Hit Blocks": N,      +
+       "Shared Read Blocks": N,     +
+       "Shared Dirtied Blocks": N,  +
+       "Shared Written Blocks": N,  +
+       "Local Hit Blocks": N,       +
+       "Local Read Blocks": N,      +
+       "Local Dirtied Blocks": N,   +
+       "Local Written Blocks": N,   +
+       "Temp Read Blocks": N,       +
+       "Temp Written Blocks": N,    +
+       "Shared I/O Read Time": N.N, +
+       "Shared I/O Write Time": N.N,+
+       "Local I/O Read Time": N.N,  +
+       "Local I/O Write Time": N.N, +
+       "Temp I/O Read Time": N.N,   +
+       "Temp I/O Write Time": N.N   +
+     },                             +
+     "Planning": {                  +
+       "Shared Hit Blocks": N,      +
+       "Shared Read Blocks": N,     +
+       "Shared Dirtied Blocks": N,  +
+       "Shared Written Blocks": N,  +
+       "Local Hit Blocks": N,       +
+       "Local Read Blocks": N,      +
+       "Local Dirtied Blocks": N,   +
+       "Local Written Blocks": N,   +
+       "Temp Read Blocks": N,       +
+       "Temp Written Blocks": N,    +
+       "Shared I/O Read Time": N.N, +
+       "Shared I/O Write Time": N.N,+
+       "Local I/O Read Time": N.N,  +
+       "Local I/O Write Time": N.N, +
+       "Temp I/O Read Time": N.N,   +
+       "Temp I/O Write Time": N.N,  +
+       "Storage I/O Read": N,       +
+       "Storage I/O Write": N       +
+     },                             +
+     "Planning Time": N.N,          +
+     "Triggers": [                  +
+     ],                             +
+     "Execution": {                 +
+       "Storage I/O Read": N,       +
+       "Storage I/O Write": N       +
+     },                             +
+     "Execution Time": N.N          +
+   }                                +
+ ]
+(1 row)
+
+set track_io_timing = off;
+-- SETTINGS option
+-- We have to ignore other settings that might be imposed by the environment,
+-- so printing the whole Settings field unfortunately won't do.
+begin;
+set local plan_cache_mode = force_generic_plan;
+select true as "OK"
+  from explain_filter('explain (settings) select * from int8_tbl i8') ln
+  where ln ~ '^ *Settings: .*plan_cache_mode = ''force_generic_plan''';
+ OK 
+----
+ t
+(1 row)
+
+select explain_filter_to_json('explain (settings, format json) select * from int8_tbl i8') #> '{0,Settings,plan_cache_mode}';
+       ?column?       
+----------------------
+ "force_generic_plan"
+(1 row)
+
+rollback;
+-- GENERIC_PLAN option
+select explain_filter('explain (generic_plan) select unique1 from tenk1 where thousand = $1');
+                                 explain_filter                                  
+---------------------------------------------------------------------------------
+ Bitmap Heap Scan on tenk1  (cost=N.N..N.N rows=N width=N)
+   Recheck Cond: (thousand = $N)
+   ->  Bitmap Index Scan on tenk1_thous_tenthous  (cost=N.N..N.N rows=N width=N)
+         Index Cond: (thousand = $N)
+(4 rows)
+
+-- should fail
+select explain_filter('explain (analyze, generic_plan) select unique1 from tenk1 where thousand = $1');
+ERROR:  EXPLAIN options ANALYZE and GENERIC_PLAN cannot be used together
+CONTEXT:  PL/pgSQL function explain_filter(text) line 5 at FOR over EXECUTE statement
+-- MEMORY option
+select explain_filter('explain (memory) select * from int8_tbl i8');
+                     explain_filter                      
+---------------------------------------------------------
+ Seq Scan on int8_tbl i8  (cost=N.N..N.N rows=N width=N)
+   Memory: used=NkB  allocated=NkB
+(2 rows)
+
+select explain_filter('explain (memory, analyze, buffers off) select * from int8_tbl i8');
+                                         explain_filter                                          
+-------------------------------------------------------------------------------------------------
+ Seq Scan on int8_tbl i8  (cost=N.N..N.N rows=N width=N) (actual time=N.N..N.N rows=N.N loops=N)
+   Memory: used=NkB  allocated=NkB
+ Planning Time: N.N ms
+ Execution Time: N.N ms
+(4 rows)
+
+select explain_filter('explain (memory, summary, format yaml) select * from int8_tbl i8');
+        explain_filter         
+-------------------------------
+ - Plan:                      +
+     Node Type: "Seq Scan"    +
+     Parallel Aware: false    +
+     Async Capable: false     +
+     Relation Name: "int8_tbl"+
+     Alias: "i8"              +
+     Startup Cost: N.N        +
+     Total Cost: N.N          +
+     Plan Rows: N             +
+     Plan Width: N            +
+     Disabled: false          +
+   Planning:                  +
+     Memory Used: N           +
+     Memory Allocated: N      +
+   Planning Time: N.N
+(1 row)
+
+select explain_filter('explain (memory, analyze, format json) select * from int8_tbl i8');
+           explain_filter           
+------------------------------------
+ [                                 +
+   {                               +
+     "Plan": {                     +
+       "Node Type": "Seq Scan",    +
+       "Parallel Aware": false,    +
+       "Async Capable": false,     +
+       "Relation Name": "int8_tbl",+
+       "Alias": "i8",              +
+       "Startup Cost": N.N,        +
+       "Total Cost": N.N,          +
+       "Plan Rows": N,             +
+       "Plan Width": N,            +
+       "Actual Startup Time": N.N, +
+       "Actual Total Time": N.N,   +
+       "Actual Rows": N.N,         +
+       "Actual Loops": N,          +
+       "Disabled": false,          +
+       "Shared Hit Blocks": N,     +
+       "Shared Read Blocks": N,    +
+       "Shared Dirtied Blocks": N, +
+       "Shared Written Blocks": N, +
+       "Local Hit Blocks": N,      +
+       "Local Read Blocks": N,     +
+       "Local Dirtied Blocks": N,  +
+       "Local Written Blocks": N,  +
+       "Temp Read Blocks": N,      +
+       "Temp Written Blocks": N    +
+     },                            +
+     "Planning": {                 +
+       "Shared Hit Blocks": N,     +
+       "Shared Read Blocks": N,    +
+       "Shared Dirtied Blocks": N, +
+       "Shared Written Blocks": N, +
+       "Local Hit Blocks": N,      +
+       "Local Read Blocks": N,     +
+       "Local Dirtied Blocks": N,  +
+       "Local Written Blocks": N,  +
+       "Temp Read Blocks": N,      +
+       "Temp Written Blocks": N,   +
+       "Storage I/O Read": N,      +
+       "Storage I/O Write": N,     +
+       "Memory Used": N,           +
+       "Memory Allocated": N       +
+     },                            +
+     "Planning Time": N.N,         +
+     "Triggers": [                 +
+     ],                            +
+     "Execution": {                +
+       "Storage I/O Read": N,      +
+       "Storage I/O Write": N      +
+     },                            +
+     "Execution Time": N.N         +
+   }                               +
+ ]
+(1 row)
+
+prepare int8_query as select * from int8_tbl i8;
+select explain_filter('explain (memory) execute int8_query');
+                     explain_filter                      
+---------------------------------------------------------
+ Seq Scan on int8_tbl i8  (cost=N.N..N.N rows=N width=N)
+   Memory: used=NkB  allocated=NkB
+(2 rows)
+
+-- Test EXPLAIN (GENERIC_PLAN) with partition pruning
+-- partitions should be pruned at plan time, based on constants,
+-- but there should be no pruning based on parameter placeholders
+create table gen_part (
+  key1 integer not null,
+  key2 integer not null
+) partition by list (key1);
+create table gen_part_1
+  partition of gen_part for values in (1)
+  partition by range (key2);
+create table gen_part_1_1
+  partition of gen_part_1 for values from (1) to (2);
+create table gen_part_1_2
+  partition of gen_part_1 for values from (2) to (3);
+create table gen_part_2
+  partition of gen_part for values in (2);
+-- should scan gen_part_1_1 and gen_part_1_2, but not gen_part_2
+select explain_filter('explain (generic_plan) select key1, key2 from gen_part where key1 = 1 and key2 = $1');
+                              explain_filter                               
+---------------------------------------------------------------------------
+ Append  (cost=N.N..N.N rows=N width=N)
+   ->  Seq Scan on gen_part_1_1 gen_part_1  (cost=N.N..N.N rows=N width=N)
+         Filter: ((key1 = N) AND (key2 = $N))
+   ->  Seq Scan on gen_part_1_2 gen_part_2  (cost=N.N..N.N rows=N width=N)
+         Filter: ((key1 = N) AND (key2 = $N))
+(5 rows)
+
+drop table gen_part;
+--
+-- Test production of per-worker data
+--
+-- Unfortunately, because we don't know how many worker processes we'll
+-- actually get (maybe none at all), we can't examine the "Workers" output
+-- in any detail.  We can check that it parses correctly as JSON, and then
+-- remove it from the displayed results.
+begin;
+-- encourage use of parallel plans
+set parallel_setup_cost=0;
+set parallel_tuple_cost=0;
+set min_parallel_table_scan_size=0;
+set max_parallel_workers_per_gather=4;
+select jsonb_pretty(
+  explain_filter_to_json('explain (analyze, verbose, buffers, format json)
+                         select * from tenk1 order by tenthous')
+  -- remove "Workers" node of the Seq Scan plan node
+  #- '{0,Plan,Plans,0,Plans,0,Workers}'
+  -- remove "Workers" node of the Sort plan node
+  #- '{0,Plan,Plans,0,Workers}'
+  -- Also remove its sort-type fields, as those aren't 100% stable
+  #- '{0,Plan,Plans,0,Sort Method}'
+  #- '{0,Plan,Plans,0,Sort Space Type}'
+);
+                        jsonb_pretty                         
+-------------------------------------------------------------
+ [                                                          +
+     {                                                      +
+         "Plan": {                                          +
+             "Plans": [                                     +
+                 {                                          +
+                     "Plans": [                             +
+                         {                                  +
+                             "Alias": "tenk1",              +
+                             "Output": [                    +
+                                 "unique1",                 +
+                                 "unique2",                 +
+                                 "two",                     +
+                                 "four",                    +
+                                 "ten",                     +
+                                 "twenty",                  +
+                                 "hundred",                 +
+                                 "thousand",                +
+                                 "twothousand",             +
+                                 "fivethous",               +
+                                 "tenthous",                +
+                                 "odd",                     +
+                                 "even",                    +
+                                 "stringu1",                +
+                                 "stringu2",                +
+                                 "string4"                  +
+                             ],                             +
+                             "Schema": "public",            +
+                             "Disabled": false,             +
+                             "Node Type": "Seq Scan",       +
+                             "Plan Rows": 0,                +
+                             "Plan Width": 0,               +
+                             "Total Cost": 0.0,             +
+                             "Actual Rows": 0.0,            +
+                             "Actual Loops": 0,             +
+                             "Startup Cost": 0.0,           +
+                             "Async Capable": false,        +
+                             "Relation Name": "tenk1",      +
+                             "Parallel Aware": true,        +
+                             "Local Hit Blocks": 0,         +
+                             "Temp Read Blocks": 0,         +
+                             "Actual Total Time": 0.0,      +
+                             "Local Read Blocks": 0,        +
+                             "Shared Hit Blocks": 0,        +
+                             "Shared Read Blocks": 0,       +
+                             "Actual Startup Time": 0.0,    +
+                             "Parent Relationship": "Outer",+
+                             "Temp Written Blocks": 0,      +
+                             "Local Dirtied Blocks": 0,     +
+                             "Local Written Blocks": 0,     +
+                             "Shared Dirtied Blocks": 0,    +
+                             "Shared Written Blocks": 0     +
+                         }                                  +
+                     ],                                     +
+                     "Output": [                            +
+                         "unique1",                         +
+                         "unique2",                         +
+                         "two",                             +
+                         "four",                            +
+                         "ten",                             +
+                         "twenty",                          +
+                         "hundred",                         +
+                         "thousand",                        +
+                         "twothousand",                     +
+                         "fivethous",                       +
+                         "tenthous",                        +
+                         "odd",                             +
+                         "even",                            +
+                         "stringu1",                        +
+                         "stringu2",                        +
+                         "string4"                          +
+                     ],                                     +
+                     "Disabled": false,                     +
+                     "Sort Key": [                          +
+                         "tenk1.tenthous"                   +
+                     ],                                     +
+                     "Node Type": "Sort",                   +
+                     "Plan Rows": 0,                        +
+                     "Plan Width": 0,                       +
+                     "Total Cost": 0.0,                     +
+                     "Actual Rows": 0.0,                    +
+                     "Actual Loops": 0,                     +
+                     "Startup Cost": 0.0,                   +
+                     "Async Capable": false,                +
+                     "Parallel Aware": false,               +
+                     "Sort Space Used": 0,                  +
+                     "Local Hit Blocks": 0,                 +
+                     "Temp Read Blocks": 0,                 +
+                     "Actual Total Time": 0.0,              +
+                     "Local Read Blocks": 0,                +
+                     "Shared Hit Blocks": 0,                +
+                     "Shared Read Blocks": 0,               +
+                     "Actual Startup Time": 0.0,            +
+                     "Parent Relationship": "Outer",        +
+                     "Temp Written Blocks": 0,              +
+                     "Local Dirtied Blocks": 0,             +
+                     "Local Written Blocks": 0,             +
+                     "Shared Dirtied Blocks": 0,            +
+                     "Shared Written Blocks": 0             +
+                 }                                          +
+             ],                                             +
+             "Output": [                                    +
+                 "unique1",                                 +
+                 "unique2",                                 +
+                 "two",                                     +
+                 "four",                                    +
+                 "ten",                                     +
+                 "twenty",                                  +
+                 "hundred",                                 +
+                 "thousand",                                +
+                 "twothousand",                             +
+                 "fivethous",                               +
+                 "tenthous",                                +
+                 "odd",                                     +
+                 "even",                                    +
+                 "stringu1",                                +
+                 "stringu2",                                +
+                 "string4"                                  +
+             ],                                             +
+             "Disabled": false,                             +
+             "Node Type": "Gather Merge",                   +
+             "Plan Rows": 0,                                +
+             "Plan Width": 0,                               +
+             "Total Cost": 0.0,                             +
+             "Actual Rows": 0.0,                            +
+             "Actual Loops": 0,                             +
+             "Startup Cost": 0.0,                           +
+             "Async Capable": false,                        +
+             "Parallel Aware": false,                       +
+             "Workers Planned": 0,                          +
+             "Local Hit Blocks": 0,                         +
+             "Temp Read Blocks": 0,                         +
+             "Workers Launched": 0,                         +
+             "Actual Total Time": 0.0,                      +
+             "Local Read Blocks": 0,                        +
+             "Shared Hit Blocks": 0,                        +
+             "Shared Read Blocks": 0,                       +
+             "Actual Startup Time": 0.0,                    +
+             "Temp Written Blocks": 0,                      +
+             "Local Dirtied Blocks": 0,                     +
+             "Local Written Blocks": 0,                     +
+             "Shared Dirtied Blocks": 0,                    +
+             "Shared Written Blocks": 0                     +
+         },                                                 +
+         "Planning": {                                      +
+             "Local Hit Blocks": 0,                         +
+             "Storage I/O Read": 0,                         +
+             "Temp Read Blocks": 0,                         +
+             "Local Read Blocks": 0,                        +
+             "Shared Hit Blocks": 0,                        +
+             "Storage I/O Write": 0,                        +
+             "Shared Read Blocks": 0,                       +
+             "Temp Written Blocks": 0,                      +
+             "Local Dirtied Blocks": 0,                     +
+             "Local Written Blocks": 0,                     +
+             "Shared Dirtied Blocks": 0,                    +
+             "Shared Written Blocks": 0                     +
+         },                                                 +
+         "Triggers": [                                      +
+         ],                                                 +
+         "Execution": {                                     +
+             "Storage I/O Read": 0,                         +
+             "Storage I/O Write": 0                         +
+         },                                                 +
+         "Planning Time": 0.0,                              +
+         "Execution Time": 0.0                              +
+     }                                                      +
+ ]
+(1 row)
+
+rollback;
+-- Test display of temporary objects
+create temp table t1(f1 float8);
+create function pg_temp.mysin(float8) returns float8 language plpgsql
+as 'begin return sin($1); end';
+select explain_filter('explain (verbose) select * from t1 where pg_temp.mysin(f1) < 0.5');
+                       explain_filter                       
+------------------------------------------------------------
+ Seq Scan on pg_temp.t1  (cost=N.N..N.N rows=N width=N)
+   Output: f1
+   Filter: (pg_temp.mysin(t1.f1) < 'N.N'::double precision)
+(3 rows)
+
+-- Test compute_query_id
+set compute_query_id = on;
+select explain_filter('explain (verbose) select * from int8_tbl i8');
+                         explain_filter                         
+----------------------------------------------------------------
+ Seq Scan on public.int8_tbl i8  (cost=N.N..N.N rows=N width=N)
+   Output: q1, q2
+ Query Identifier: N
+(3 rows)
+
+-- Test compute_query_id with utility statements containing plannable query
+select explain_filter('explain (verbose) declare test_cur cursor for select * from int8_tbl');
+                       explain_filter                        
+-------------------------------------------------------------
+ Seq Scan on public.int8_tbl  (cost=N.N..N.N rows=N width=N)
+   Output: q1, q2
+ Query Identifier: N
+(3 rows)
+
+select explain_filter('explain (verbose) create table test_ctas as select 1');
+             explain_filter             
+----------------------------------------
+ Result  (cost=N.N..N.N rows=N width=N)
+   Output: N
+ Query Identifier: N
+(3 rows)
+
+-- Test SERIALIZE option
+select explain_filter('explain (analyze,buffers off,serialize) select * from int8_tbl i8');
+                                         explain_filter                                          
+-------------------------------------------------------------------------------------------------
+ Seq Scan on int8_tbl i8  (cost=N.N..N.N rows=N width=N) (actual time=N.N..N.N rows=N.N loops=N)
+ Planning Time: N.N ms
+ Serialization: time=N.N ms  output=NkB  format=text
+ Execution Time: N.N ms
+(4 rows)
+
+select explain_filter('explain (analyze,serialize text,buffers,timing off) select * from int8_tbl i8');
+                                  explain_filter                                   
+-----------------------------------------------------------------------------------
+ Seq Scan on int8_tbl i8  (cost=N.N..N.N rows=N width=N) (actual rows=N.N loops=N)
+ Planning Time: N.N ms
+ Serialization: output=NkB  format=text
+ Execution Time: N.N ms
+(4 rows)
+
+select explain_filter('explain (analyze,serialize binary,buffers,timing) select * from int8_tbl i8');
+                                         explain_filter                                          
+-------------------------------------------------------------------------------------------------
+ Seq Scan on int8_tbl i8  (cost=N.N..N.N rows=N width=N) (actual time=N.N..N.N rows=N.N loops=N)
+ Planning Time: N.N ms
+ Serialization: time=N.N ms  output=NkB  format=binary
+ Execution Time: N.N ms
+(4 rows)
+
+-- this tests an edge case where we have no data to return
+select explain_filter('explain (analyze,buffers off,serialize) create temp table explain_temp as select * from int8_tbl i8');
+                                         explain_filter                                          
+-------------------------------------------------------------------------------------------------
+ Seq Scan on int8_tbl i8  (cost=N.N..N.N rows=N width=N) (actual time=N.N..N.N rows=N.N loops=N)
+ Planning Time: N.N ms
+ Serialization: time=N.N ms  output=NkB  format=text
+ Execution Time: N.N ms
+(4 rows)
+
+-- Test tuplestore storage usage in Window aggregate (memory case)
+select explain_filter('explain (analyze,buffers off,costs off) select sum(n) over() from generate_series(1,10) a(n)');
+                                  explain_filter                                  
+----------------------------------------------------------------------------------
+ WindowAgg (actual time=N.N..N.N rows=N.N loops=N)
+   Window: w1 AS ()
+   Storage: Memory  Maximum Storage: NkB
+   ->  Function Scan on generate_series a (actual time=N.N..N.N rows=N.N loops=N)
+ Planning Time: N.N ms
+ Execution Time: N.N ms
+(6 rows)
+
+-- Test tuplestore storage usage in Window aggregate (disk case)
+set work_mem to 64;
+select explain_filter('explain (analyze,buffers off,costs off) select sum(n) over() from generate_series(1,2500) a(n)');
+                                  explain_filter                                  
+----------------------------------------------------------------------------------
+ WindowAgg (actual time=N.N..N.N rows=N.N loops=N)
+   Window: w1 AS ()
+   Storage: Disk  Maximum Storage: NkB
+   ->  Function Scan on generate_series a (actual time=N.N..N.N rows=N.N loops=N)
+ Planning Time: N.N ms
+ Execution Time: N.N ms
+(6 rows)
+
+-- Test tuplestore storage usage in Window aggregate (memory and disk case, final result is disk)
+select explain_filter('explain (analyze,buffers off,costs off) select sum(n) over(partition by m) from (SELECT n < 3 as m, n from generate_series(1,2500) a(n))');
+                                     explain_filter                                     
+----------------------------------------------------------------------------------------
+ WindowAgg (actual time=N.N..N.N rows=N.N loops=N)
+   Window: w1 AS (PARTITION BY ((a.n < N)))
+   Storage: Disk  Maximum Storage: NkB
+   ->  Sort (actual time=N.N..N.N rows=N.N loops=N)
+         Sort Key: ((a.n < N))
+         Sort Method: external merge  Disk: NkB
+         ->  Function Scan on generate_series a (actual time=N.N..N.N rows=N.N loops=N)
+ Planning Time: N.N ms
+ Execution Time: N.N ms
+(9 rows)
+
+reset work_mem;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 8cf40c87043..b1d7fd9d33a 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2779,6 +2779,7 @@ SSL
 SSLExtensionInfoContext
 SSL_CTX
 STARTUPINFO
+StorageIOUsage
 STRLEN
 SV
 SYNCHRONIZATION_BARRIER
-- 
2.43.0



^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* Re: RFC: Allow EXPLAIN to Output Page Fault Information
@ 2026-05-24 09:50  Jelte Fennema-Nio <[email protected]>
  parent: Atsushi Torikoshi <[email protected]>
  1 sibling, 1 reply; 283+ messages in thread

From: Jelte Fennema-Nio @ 2026-05-24 09:50 UTC (permalink / raw)
  To: Atsushi Torikoshi <[email protected]>; +Cc: vellaipandiyan sm <[email protected]>; torikoshia <[email protected]>; pgsql-hackers; Tomas Vondra <[email protected]>

On Fri, 22 May 2026 at 18:07, Atsushi Torikoshi
<[email protected]> wrote:
> Updated the patch to clarify that the reported values include not only
> the backend process executing the query, but also any parallel query
> worker processes involved in the query.

For PG19 Tomas added an IO option to EXPLAIN. I think it would be
better to have the Storage IO tracking be enabled by the IO option,
rather than the BUFFERS option.






^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* Re: RFC: Allow EXPLAIN to Output Page Fault Information
@ 2026-05-25 12:17  Atsushi Torikoshi <[email protected]>
  parent: Jelte Fennema-Nio <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Atsushi Torikoshi @ 2026-05-25 12:17 UTC (permalink / raw)
  To: Jelte Fennema-Nio <[email protected]>; +Cc: torikoshia <[email protected]>; pgsql-hackers; Tomas Vondra <[email protected]>

On Sun, May 24, 2026 at 6:50 PM Jelte Fennema-Nio <[email protected]> wrote:
>
> On Fri, 22 May 2026 at 18:07, Atsushi Torikoshi
> <[email protected]> wrote:
> > Updated the patch to clarify that the reported values include not only
> > the backend process executing the query, but also any parallel query
> > worker processes involved in the query.
>
> For PG19 Tomas added an IO option to EXPLAIN. I think it would be
> better to have the Storage IO tracking be enabled by the IO option,
> rather than the BUFFERS option.

Thank you for pointing that out.
I agree that having this under the IO option seems more intuitive.

One thing I am slightly concerned about, though, is that according to
the documentation, the IO option reports only I/O performed by scan
nodes:

> Include information on I/O performed by scan nodes providing such information.

In contrast, the information produced by this patch is based on
getrusage(), so it includes all Storage I/O performed by the backend
and parallel workers, not just scan nodes.
For example, it would also include temporary file I/O generated by
operations such as sorts that spill to disk when they exceed work_mem.

I suppose this could be clarified in the documentation, but I would be
interested to hear if anyone has concerns or objections about that
approach.

--
Regards,
Atsushi Torikoshi





^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* Re: RFC: Allow EXPLAIN to Output Page Fault Information
@ 2026-05-25 18:43  Lukas Fittl <[email protected]>
  parent: Atsushi Torikoshi <[email protected]>
  1 sibling, 1 reply; 283+ messages in thread

From: Lukas Fittl @ 2026-05-25 18:43 UTC (permalink / raw)
  To: Atsushi Torikoshi <[email protected]>; +Cc: vellaipandiyan sm <[email protected]>; torikoshia <[email protected]>; pgsql-hackers; Andres Freund <[email protected]>; Jeremy Schneider <[email protected]>

On Fri, May 22, 2026 at 9:07 AM Atsushi Torikoshi
<[email protected]> wrote:
>
> Thanks for the review!
>
> On Thu, May 21, 2026 at 2:38 PM vellaipandiyan sm
> <[email protected]> wrote:
> >
> > Hello hackers,
> >
> > I reviewed the EXPLAIN storage I/O patch and the overall direction seems useful, especially for distinguishing shared-buffer hits from actual storage reads during query analysis.
> >
> > One concern that stood out to me from the later discussion is the interaction with asynchronous I/O and worker-based I/O accounting.
> >
> > Since the patch currently relies on per-process getrusage() statistics, it seems possible that the reported values could become partial or misleading once I/O is performed outside the backend process context. In particular, worker-based AIO could undercount storage reads/writes while still returning non-zero values, which may make the output appear more accurate than it actually is.
>
> Yeah, to avoid reporting the misleadingly underestimated values, no
> output is shown when worker-based AIO is used, as described in the
> docs:

I think having something like this patch proposes would be extremely
valuable, but:

Do we even have a path forward here if this simply won't work with I/O workers?

This was discussed before on this thread, but if anything it seems to
me the situation has become more clear that I/O workers are going to
be used for the majority of Postgres 19+ installations.

At least for my part, I've seen both managed providers only offering
I/O workers (e.g. AWS RDS/Aurora), as well as challenges in container
environments where io_uring is not enabled.

Maybe we should try to figure out what would be needed to do better
I/O tracking on the Linux side in a way that is compatible with I/O
workers?

e.g. I assume rusage is too expensive to run on individual I/Os that
the workers process (so its not just a communication problem) -- but
would be good to benchmark.

Thanks,
Lukas

-- 
Lukas Fittl






^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* Re: RFC: Allow EXPLAIN to Output Page Fault Information
@ 2026-05-30 09:44  Ilmar Y <[email protected]>
  parent: Lukas Fittl <[email protected]>
  0 siblings, 1 reply; 283+ messages in thread

From: Ilmar Y @ 2026-05-30 09:44 UTC (permalink / raw)
  To: [email protected]; +Cc: Atsushi Torikoshi <[email protected]>

The following review has been posted through the commitfest application:
make installcheck-world:  not tested
Implements feature:       tested, failed
Spec compliant:           not tested
Documentation:            not tested

Hi,

I looked at v11, focusing on structured EXPLAIN output and a small local
build/test pass.

The patch applies cleanly on current master at
db5ed03217b9c238703df8b4b286115d6e940488, but git am warned about trailing
whitespace.  git diff --check origin/master...HEAD reports:

src/test/modules/test_misc/t/011_explain_storage_io.pl:47: trailing whitespace
src/test/modules/test_misc/t/011_explain_storage_io.pl:55: trailing whitespace
src/test/modules/test_misc/t/011_explain_storage_io.pl:61: trailing whitespace

A second thing I noticed is that, with io_method=sync, structured EXPLAIN
output can show an Execution Storage I/O section even when ANALYZE is not
used.

For example:

CREATE TABLE t AS SELECT generate_series(1, 3) AS a;
EXPLAIN (BUFFERS, FORMAT JSON) SELECT * FROM t;

returns, in part:

    "Planning": {
      ...
      "Storage I/O Read": 0,
      "Storage I/O Write": 0
    },
    "Execution": {
      "Storage I/O Read": 0,
      "Storage I/O Write": 0
    }

The same happens with FORMAT XML and FORMAT YAML.  The query was not
executed, so I don't think an Execution section should be emitted here.

The existing BUFFERS documentation says that when BUFFERS is true without
ANALYZE, only buffer usage during query planning is reported.  Since this
output is under BUFFERS, an Execution Storage I/O section without ANALYZE
looks surprising to me.

For comparison, text output for the same query reports only the Planning
section and has no Execution section:

Planning:
  Buffers: shared hit=12 read=7

It looks like this comes from ExplainOnePlan() considering execution Storage
I/O whenever es->buffers is true, and peek_storageio_usage() returning true
for non-text formats even when both counters are zero.  Should the execution
Storage I/O section be gated on es->analyze, similar to Execution Time?

Local checks I ran:

git diff --check origin/master...HEAD: failed with the whitespace issue above
./configure --prefix="$PWD/pg-install" --without-readline --without-zlib --without-icu: passed
make -s -j8: passed
make -s install: passed
make -C src/test/regress check TESTS=explain: passed

I tried to run the new TAP test, but this local environment is missing the
IPC::Run Perl module required by --enable-tap-tests, so I could not verify it
locally.

I could not test Linux io_uring behavior in this local macOS environment, and
I have not benchmarked the getrusage() overhead.

Regards,
Ilmar Yunusov

The new status of this patch is: Waiting on Author


^ permalink  raw  reply  [nested|flat] 283+ messages in thread

* Re: RFC: Allow EXPLAIN to Output Page Fault Information
@ 2026-06-01 13:10  Atsushi Torikoshi <[email protected]>
  parent: Ilmar Y <[email protected]>
  0 siblings, 0 replies; 283+ messages in thread

From: Atsushi Torikoshi @ 2026-06-01 13:10 UTC (permalink / raw)
  To: Ilmar Y <[email protected]>; Lukas Fittl <[email protected]>; +Cc: [email protected]; Atsushi Torikoshi <[email protected]>

On Tue, May 26, 2026 at 3:44 AM Lukas Fittl <[email protected]> wrote:

Thanks for your comment!

> Maybe we should try to figure out what would be needed to do better
> I/O tracking on the Linux side in a way that is compatible with I/O
> workers?

That may well be true.
Unfortunately, I do not currently have a good idea of how to achieve
this in a way that works with I/O workers.
 I'll keep thinking about whether there might be another approach.


> e.g. I assume rusage is too expensive to run on individual I/Os that
> the workers process (so its not just a communication problem) -- but
> would be good to benchmark.

Yes, I suspect that would be the case.
Although this is somewhat different from the current discussion, I
once experimented with an implementation that called getrusage() for
each plan node, and the overhead was high enough that it was not
practically usable. [1]


I agree that many users will choose, or be required to choose,
io_method = worker. However, there are also users who will continue
to use sync or choose io_uring, so I do not think providing I/O
statistics for those users would be without value.

In particular, from a performance perspective, io_uring seems
likely to be the preferred option in the long run.
In high-performance on-premises environments, for example, it would
not be surprising to see users selecting io_uring.
Those users would also be among those most interested in
understanding how much I/O is being generated against storage,
which is the motivation behind this proposal.



On Sat, May 30, 2026 at 6:45 PM Ilmar Y <[email protected]> wrote:

Thanks for your review!

> The patch applies cleanly on current master at
> db5ed03217b9c238703df8b4b286115d6e940488, but git am warned about trailing
> whitespace.  git diff --check origin/master...HEAD reports:

> src/test/modules/test_misc/t/011_explain_storage_io.pl:47: trailing whitespace
> src/test/modules/test_misc/t/011_explain_storage_io.pl:55: trailing whitespace
> src/test/modules/test_misc/t/011_explain_storage_io.pl:61: trailing whitespace

I'll fix it.

> A second thing I noticed is that, with io_method=sync, structured EXPLAIN
> output can show an Execution Storage I/O section even when ANALYZE is not
> used.

We are currently considering moving this functionality to a new IO option that,
unlike BUFFERS, would require ANALYZE to be specified.[2]

[1] https://www.postgresql.org/message-id/CAGXjcj%3DhnEZCCDDMRv06EQnDcv0mRe6%2BPh1gv8%3DHb7NEc51y5A%40ma...
[2] https://www.postgresql.org/message-id/CAM6-o%3DBL59LgruKXm3DCjzFzvr7TTJPtryEPj51YeGMFrWO0EQ%40mail.g...

---
Regards,

Atsushi Torikoshi






^ permalink  raw  reply  [nested|flat] 283+ messages in thread


end of thread, other threads:[~2026-06-01 13:10 UTC | newest]

Thread overview: 283+ messages (download: mbox mbox.gz follow: Atom feed)
-- links below jump to the message on this page --
2018-11-07 07:53 [PATCH 3/5] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2018-11-07 07:53 [PATCH v24 3/5] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v46 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v45 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v47 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v47 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v39 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v47 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v46 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v45 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v31 4/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v46 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v47 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v41 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v46 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v45 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v47 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v47 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v45 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v29 4/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v45 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v47 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v36 4/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v45 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v32 4/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v47 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v47 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v46 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v33 4/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v46 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v47 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v46 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v47 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v38 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v46 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v25 4/8] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v46 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v30 4/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v46 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v45 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v47 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v45 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v45 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v40 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v43 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v47 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v46 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v33 4/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v45 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v45 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v46 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v45 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v46 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v45 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v47 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v45 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v45 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v35 4/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v45 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v46 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v34 4/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v47 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v47 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v47 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v44 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v46 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v47 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v46 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v46 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v45 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v47 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v46 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v45 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v45 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v46 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v50 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v45 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v51 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v37 3/6] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v47 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v46 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v45 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v48 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v46 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v47 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v49 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v42 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2020-03-13 07:59 [PATCH v52 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v55 3/3] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v53 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2021-03-11 09:01 [PATCH v54 3/7] Make archiver process an auxiliary process Kyotaro Horiguchi <[email protected]>
2024-12-24 08:53 RFC: Allow EXPLAIN to Output Page Fault Information torikoshia <[email protected]>
2026-05-21 05:38 ` Re: RFC: Allow EXPLAIN to Output Page Fault Information vellaipandiyan sm <[email protected]>
2026-05-22 16:07   ` Re: RFC: Allow EXPLAIN to Output Page Fault Information Atsushi Torikoshi <[email protected]>
2026-05-24 09:50     ` Re: RFC: Allow EXPLAIN to Output Page Fault Information Jelte Fennema-Nio <[email protected]>
2026-05-25 12:17       ` Re: RFC: Allow EXPLAIN to Output Page Fault Information Atsushi Torikoshi <[email protected]>
2026-05-25 18:43     ` Re: RFC: Allow EXPLAIN to Output Page Fault Information Lukas Fittl <[email protected]>
2026-05-30 09:44       ` Re: RFC: Allow EXPLAIN to Output Page Fault Information Ilmar Y <[email protected]>
2026-06-01 13:10         ` Re: RFC: Allow EXPLAIN to Output Page Fault Information Atsushi Torikoshi <[email protected]>

This inbox is served by agora; see mirroring instructions
for how to clone and mirror all data and code used for this inbox